V11.

cover

Front cover
Course Guide
Artificial Intelligence Analyst 2019
Course code SAAI   ERC 1.0
January 2019 edition
Notices
This information was developed for products and services offered in the US.
IBM may not offer the products, services, or features discussed in this document in other countries. Consult your local IBM representative
for information on the products and services currently available in your area. Any reference to an IBM product, program, or service is not
intended to state or imply that only that IBM product, program, or service may be used. Any functionally equivalent product, program, or
service that does not infringe any IBM intellectual property right may be used instead. However, it is the user's responsibility to evaluate
and verify the operation of any non-IBM product, program, or service.
IBM may have patents or pending patent applications covering subject matter described in this document. The furnishing of this
document does not grant you any license to these patents. You can send license inquiries, in writing, to:
IBM Director of Licensing
IBM Corporation
North Castle Drive, MD-NC119
Armonk, NY 10504-1785
United States of America
INTERNATIONAL BUSINESS MACHINES CORPORATION PROVIDES THIS PUBLICATION "AS IS" WITHOUT WARRANTY OF ANY
KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Some jurisdictions do not allow disclaimer
of express or implied warranties in certain transactions, therefore, this statement may not apply to you.
This information could include technical inaccuracies or typographical errors. Changes are periodically made to the information herein;
these changes will be incorporated in new editions of the publication. IBM may make improvements and/or changes in the product(s)
and/or the program(s) described in this publication at any time without notice.
Any references in this information to non-IBM websites are provided for convenience only and do not in any manner serve as an
endorsement of those websites. The materials at those websites are not part of the materials for this IBM product and use of those
websites is at your own risk.
IBM may use or distribute any of the information you provide in any way it believes appropriate without incurring any obligation to you.
Information concerning non-IBM products was obtained from the suppliers of those products, their published announcements or other
publicly available sources. IBM has not tested those products and cannot confirm the accuracy of performance, compatibility or any other
claims related to non-IBM products. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those
products.
This information contains examples of data and reports used in daily business operations. To illustrate them as completely as possible,
the examples include the names of individuals, companies, brands, and products. All of these names are fictitious and any similarity to
actual people or business enterprises is entirely coincidental.
Trademarks
IBM, the IBM logo, and ibm.com are trademarks or registered trademarks of International Business Machines Corp., registered in many
jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM
trademarks is available on the web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml.
© Copyright International Business Machines Corporation 2018, 2019.
This document may not be reproduced in whole or in part without the prior written permission of IBM.
US Government Users Restricted Rights - Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp.
V11.3
Contents

TOC

Contents
Trademarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xiv

Course description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xv

Agenda . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xvii

Unit 1. Introduction to machine learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-2
1.1. What is machine learning? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-3
What is machine learning? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-5
Machine learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-6
What is a statistical model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-7
1.2. Machine learning algorithms. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-8
Machine learning algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-9
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-10
Machine learning algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-11
Machine learning approaches . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-12
Machine learning approaches (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-13
Machine learning approaches (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-14
Machine learning approaches (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-15
Machine learning algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-16
Naïve Bayes classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-17
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-18
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-19
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-20
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-21
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-22
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-23
Naïve Bayes classification (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-24
Linear regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-25
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-26
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-27
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-28
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-29
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-30
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-31
Linear regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-33
Logistic regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-34
Logistic regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-35
Logistic regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-36
Logistic regression (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-37
Support vector machine . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-38
Support vector machine (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-39
Decision tree . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-40
Decision tree (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-41
Decision tree (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-42
Decision tree (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-43
Decision tree (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-44
Decision tree (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-45

© Copyright IBM Corp. 2018, 2019 iii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC K-mean clustering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-46

K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-47
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-49
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-50
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-51
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-52
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-53
K-means clustering (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-54
1.3. What are neural networks?. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-55
What are neural networks? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-56
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-57
Neural networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-58
Neural networks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-59
Neural networks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-60
Perceptron . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-61
Neural networks: Backpropagation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-62
1.4. What is deep learning? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-63
What is deep learning? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-64
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-65
Deep learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-66
Deep learning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-67
1.5. How to evaluate a machine learning model? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-68
How to evaluate a machine learning model? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-69
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-70
Model evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-71
Model evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-73
Model evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-74
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-76
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-77
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-78
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-79
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-80
Exercise: Applying machine learning algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-81
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1-82

Unit 2. Introduction to IBM Watson. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-2
2.1. IBM Watson overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-3
IBM Watson overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-5
IBM Watson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-6
IBM Watson history . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-7
IBM Watson relies on data, information, and expertise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-9
IBM Watson services offerings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-10
2.2. IBM Watson services on IBM Cloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-11
IBM Watson services on IBM Cloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-12
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-13
Watson services on IBM Cloud - Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-14
Watson Assistant (formerly Conversation) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-16
Watson Discovery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-17
Natural Language Understanding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-19
Natural Language Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-20
Visual Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-21
Speech to Text . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-23
Text to Speech . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-25
Language Translator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-27

© Copyright IBM Corp. 2018, 2019 iv

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Personality Insights . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-28

Tone Analyzer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-30
Watson Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-31
Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-33
IBM Watson Knowledge Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-35
2.3. Build with Watson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-37
Build with Watson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-38
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-39
Building AI solutions with IBM Watson services on IBM Cloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-40
Watson services and domain adaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-41
Watson services and domain adaptation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-43
Watson services and domain adaptation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-45
Getting started with Watson services on IBM Cloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-46
Watson SDKs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-47
Additional resources for developers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-48
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-49
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-50
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-51
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-52
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-53
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-54
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-55
Exercise: Exploring Watson services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-56
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2-57

Unit 3. Introduction to IBM Watson Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-2
3.1. Watson Studio overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-3
Watson Studio overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-5
What is Watson Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-6
Correct tool for the correct job . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-8
Industry use cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-10
IBM Watson Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-11
Watson Studio offerings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-12
Watson Studio and other IBM Cloud services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-14
Watson Studio high availability (public cloud) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-15
3.2. Watson Studio components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-16
Watson Studio components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-17
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-18
Projects . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-19
Creating a project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-21
Watson Studio and Cloud Object Storage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-22
Creating a project and defining its storage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-23
Watson Studio project tabs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-24
Assets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-26
Communities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-28
Collaborating in a project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-29
Watson Studio and Spark . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-31
Spark default environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-33
Associating a Spark service . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-34
3.3. Jupyter notebook . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-35
Jupyter notebook . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-36
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-37
Jupyter notebooks overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-38
Parts of a notebook . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-40

© Copyright IBM Corp. 2018, 2019 v

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Creating notebooks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-42

Creating notebooks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-43
Coding and running notebooks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-45
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-47
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-48
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-49
Exercise: Getting started with Watson Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-51
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3-52

Unit 4. Introduction to IBM Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-2
4.1. Cross-Industry Standard Process for Data Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-3
Cross-Industry Standard Process for Data Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-5
Cross-Industry Standard Process for Data Mining overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-6
CRISP-DM lifecycle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-7
Phases in CRISP-DM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-8
4.2. Data preparation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-9
Data preparation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-10
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-11
Data preparation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-12
Data selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-13
Data selection: Samples selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-15
Data selection: Survey sampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-16
Data preprocessing: Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-18
Data preprocessing: Steps overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-19
Data preprocessing: Steps overview (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-20
4.3. Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-21
Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-22
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-23
Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-24
Watson Machine Learning features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-25
Watson Machine Learning personas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-26
Watson Machine Learning: Building the model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-27
Watson Machine Learning: Building the model (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-29
Watson Machine Learning: Deploying the model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-30
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-32
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-33
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-34
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-35
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-36
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-37
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-38
Exercise 4: Getting started with Watson Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-39
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4-40

Unit 5. Introduction to natural language processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-2
5.1. Natural language processing overview. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-3
Natural language processing overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-5
What is natural language processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-6
Natural language processing applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-7
Natural language processing challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-8
5.2. Natural language processing use cases. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-9
Natural language processing use cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-10

© Copyright IBM Corp. 2018, 2019 vi

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-11

Natural language processing use cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-12
Natural language processing use cases (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-13
Natural language processing use cases (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-14
5.3. Natural language processing basic concepts and terminology. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-15
Natural language processing basic concepts and terminology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-16
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-17
Basic concepts and terminologies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-18
Basic concepts and terminologies (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-19
Basic concepts and terminologies (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-20
Basic concepts and terminologies (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-21
Basic concepts and terminologies (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-22
5.4. Natural language processing tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-23
Natural language processing tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-24
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-25
Natural language processing tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-26
Natural language processing tools and services (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-28
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-29
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-30
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-31
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-32
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5-33

Unit 6. Natural language processing concepts and components . . . . . . . . . . . . . . . . . . . . . . . . . 6-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-2
6.1. Natural language processing categories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-3
Natural language processing categories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-5
Natural language processing categories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-6
NLU applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-7
NLG applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-8
6.2. Language ambiguities. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-9
Language ambiguities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-10
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-11
Language ambiguities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-12
Language ambiguities (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-13
6.3. Natural language processing pipeline. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-14
Natural language processing pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-15
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-16
Natural language processing pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-17
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-18
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-19
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-20
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-21
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-22
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-23
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-25
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-26
Natural language processing pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-27
6.4. Information retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-28
Information retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-29
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-30
Information retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-31
Stemming . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-32
Porter stemmer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-33
Normalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-34

© Copyright IBM Corp. 2018, 2019 vii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Term Frequency – Inverse Document Frequency . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-36

Term Frequency – Inverse Document Frequency (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-37
6.5. Information extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-38
Information extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-39
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-40
Information extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-41
Information extraction (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-42
Information extraction (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-43
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-44
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-45
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-46
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-47
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6-48

Unit 7. Natural language processing evaluation metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-2
System evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-3
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-4
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-5
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-6
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-7
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-8
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-9
System evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-10
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-11
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-12
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-13
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-14
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7-15

Unit 8. Natural language processing and IBM Watson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-2
8.1. Watson NLP services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-3
Watson NLP services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-5
Watson NLP services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-6
Information extraction by using Watson services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-7
8.2. Watson Natural Language Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-8
Watson Natural Language Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-9
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-10
Watson Natural Language Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-11
Watson Natural Language Classifier (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-13
Watson Natural Language Classifier (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-14
Watson Natural Language Classifier (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-15
8.3. Watson Natural Language Understanding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-16
Watson Natural Language Understanding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-17
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-18
Watson Natural Language Understanding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-19
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-20
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-21
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-22
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-23
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-24
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-25
Watson Natural Language Understanding (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-26
8.4. Watson Discovery. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-27

© Copyright IBM Corp. 2018, 2019 viii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Watson Discovery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-28

Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-29
Watson Discovery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-30
Discovery flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-32
Watson Discovery News . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-34
Watson Discovery News service . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-36
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-37
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-38
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-39
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-40
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-41
Exercise: Ingest, convert, enrich, and query with Watson Discovery service . . . . . . . . . . . . . . . . . . 8-42
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8-43

Unit 9. Introduction to IBM Watson Knowledge Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-2
9.1. IBM Watson Knowledge Studio overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-3
IBM Watson Knowledge Studio overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-5
What is Watson Knowledge Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-6
What is Watson Knowledge Studio (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-7
Building a machine learning model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-8
Building a rule-based model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-9
Building a rule-based model (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-10
Machine learning based model versus a rule-based model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-12
Why do we need Watson Knowledge Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-13
Why do we need Watson Knowledge Studio (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-14
9.2. Watson Knowledge Studio features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-15
Watson Knowledge Studio features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-16
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-17
Creating a workspace . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-18
Workspace resources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-19
Type system . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-20
Knowledge from Language Understanding and Extraction type system . . . . . . . . . . . . . . . . . . . . . . 9-21
Dictionary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-23
Dictionary usage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-25
CSV file dictionary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-27
Documents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-29
9.3. Adapting the system to a new domain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-30
Adapting the system to a new domain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-31
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-32
Model life cycle: End-to-end domain adaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-33
Knowledge curation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-34
Ground truth generation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-36
Model development . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-38
Model evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-40
Model deployment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-41
End-to-end domain adaptation wrap-up . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-43
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-45
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-46
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-47
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-48
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-49
Exercise: Creating a machine learning model with Watson Knowledge Studio . . . . . . . . . . . . . . . . 9-50
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9-51

© Copyright IBM Corp. 2018, 2019 ix

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Unit 10. Introduction to chatbots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-2
10.1. Chatbots overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-3
Chatbots overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-5
What is a chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-6
Chatbots in the industry . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-7
Chatbots in the industry (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-8
Chatbot history . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-9
Why now . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-11
Popular chatbots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-12
Popular chatbots (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-13
10.2. Chatbots design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-14
Chatbots design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-15
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-16
Chatbot design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-17
Chatbot design: Positioning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-19
Chatbot design: Positioning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-20
Chatbot design: Positioning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-21
Chatbot design: Positioning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-23
Chatbot design: Positioning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-24
Chatbot design: Positioning (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-25
Chatbot design: Tone and personality . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-26
Chatbot design: Tone and personality (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-27
Chatbot design: Tone and personality (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-28
Chatbot design: Tone and personality for purpose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-29
Chatbot design: Tone and personality for viewpoint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-30
Chatbot design: Tone and personality for proactivity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-31
Chatbot design: Design issues . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-32
10.3. Chatbots tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-33
Chatbots tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-34
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-35
Chatbots tools and services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-36
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-38
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-39
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-40
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-41
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10-42

Unit 11. Introduction to IBM Watson Assistant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-2
11.1. Chatbot components. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-3
Chatbot components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-5
Chatbot components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-6
11.2. Watson Assistant components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-7
Watson Assistant components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-8
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-9
Watson Assistant components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-10
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-11
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-12
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-13
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-15
Watson Assistant intents features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-16
Watson Assistant intents features (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-17
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-18

© Copyright IBM Corp. 2018, 2019 x

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Watson Assistant entity evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-19

Watson Assistant entity evaluation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-20
Watson Assistant entities features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-21
Watson Assistant entities features (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-22
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-23
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-24
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-25
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-26
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-27
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-28
Watson Assistant dialog features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-29
Watson Assistant dialog features (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-30
Watson Assistant dialog features (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-31
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-32
Watson Assistant components (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-33
11.3. Enriching the chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-35
Enriching the chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-36
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-37
Persona . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-38
Emotion and tone . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-39
Interfaces . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-40
Speech recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-41
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-42
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-43
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-44
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-45
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-46
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-47
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-48
Exercise: Getting started with Watson Assistant. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-49
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-50
Exercise: Help Desk Chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-51
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11-52

Unit 12. Introduction to computer vision . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-2
What is computer vision . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-3
Computer vision history . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-4
Computer vision applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-5
Computer vision applications (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-6
Computer vision tasks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-7
Computer vision tasks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-8
Computer vision tasks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-9
Computer vision tasks (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-10
Computer vision tools . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-11
Computer vision use cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-12
Computer vision use cases (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-13
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-14
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-15
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-16
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-17
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12-18

Unit 13. Computer vision fundamentals. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-2
13.1. Image representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-3

© Copyright IBM Corp. 2018, 2019 xi

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Image representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-4

Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-5
Image representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-6
Image representation (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-8
13.2. Computer vision pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-9
Computer vision pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-10
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-11
Computer vision pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-12
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-13
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-14
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-15
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-17
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-18
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-19
Computer vision pipeline (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-20
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-21
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-22
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13-23

Unit 14. Introduction to IBM Watson Visual Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-2
14.1. Watson Visual Recognition overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-3
Watson Visual Recognition overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-5
Watson Visual Recognition service . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-6
Watson Visual Recognition service (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-7
14.2. Visual Recognition built-in models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-8
Visual Recognition built-in models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-9
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-10
Visual Recognition built-in models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-11
Visual Recognition General model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-12
Visual Recognition General model (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-13
Visual Recognition Face model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-14
Visual Recognition Food model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-15
14.3. Custom models. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-16
Custom models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-17
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-18
Custom model training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-19
Custom model training (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-20
Custom model training (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-21
Training images examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-22
Training images examples (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-23
Updating custom models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-24
Updating custom models (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-25
Updating custom models (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-26
Custom model scores . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-27
Custom model - Example . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-28
Custom model – Example (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-29
Custom model – Example (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-30
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-31
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-32
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-33
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-34
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-35
Exercise: Classifying images with Watson Visual Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-36
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14-37

© Copyright IBM Corp. 2018, 2019 xii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Contents

TOC Unit 15. Designing and building an intelligent solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-1

Unit objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-2
15.1. Integrating IBM Watson services to build a solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-3
Integrating IBM Watson services to build a solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-4
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-5
Benefits . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-6
Building solutions with Watson services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-7
Resources for the integration of Watson services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-8
15.2. Watson Assistant integration with other services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-9
Watson Assistant integration with other services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-10
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-11
Watson Assistant integration: General outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-12
Key concepts to enable Watson Assistant integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-14
Key concepts to enable Watson Assistant integration (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-15
Key concepts to enable Watson Assistant integration (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-16
Key concepts to enable Watson Assistant integration (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-18
Key concepts to enable Watson Assistant integration (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-19
Making programmatic calls from a dialog node . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-20
Watson Assistant integration architecture with Cloud Functions . . . . . . . . . . . . . . . . . . . . . . . . . . 15-21
Making programmatic calls from a dialog node (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-22
15.3. Watson Assistant, Discovery, Natural Language Understanding, and Tone Analyzer integration flow
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-24
Watson Assistant, Discovery, Natural Language Understanding, and Tone Analyzer integration flow
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-25
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-26
Integration example: Cognitive banking chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-27
Cognitive banking chatbot integration flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-28
Building the cognitive banking chatbot application . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-29
Building the cognitive banking chatbot application (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-30
Building the cognitive banking chatbot application (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-31
Build cognitive banking chatbot application (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-32
Building the cognitive banking chatbot application (Cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-34
15.4. Knowledge Studio and Watson Discovery integration flow. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-35
Knowledge Studio and Watson Discovery integration flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-36
Topics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-37
Intelligent procurement system . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-38
Intelligent procurement system integration flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-39
Unit summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-40
Review questions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-41
Review questions (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-42
Review answers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-43
Review answers (cont.) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-44
Exercise: Creating a cognitive banking FAQ chatbot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-45
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-46
Exercise: Integrating Watson Knowledge Studio with Discovery for the procurement domain . . . . 15-47
Exercise objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15-48

© Copyright IBM Corp. 2018, 2019 xiii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Trademarks

TMK

Trademarks
The reader should recognize that the following terms, which appear in the content of this training
document, are official trademarks of IBM or other companies:
IBM, the IBM logo, and ibm.com are trademarks or registered trademarks of International Business
Machines Corp., registered in many jurisdictions worldwide.
The following are trademarks of International Business Machines Corporation, registered in many
jurisdictions worldwide:
Cloudant® dashDB® Db2®
IBM Cloud™ IBM Watson® Redbooks®
SPSS® Watson™
Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.
Microsoft and Windows are trademarks of Microsoft Corporation in the United States, other
countries, or both.
Java™ and all Java-based trademarks and logos are trademarks or registered trademarks of
Oracle and/or its affiliates.
RStudio® is a registered trademark of RStudio, Inc.
Social® is a trademark or registered trademark of TWC Product and Technology, LLC, an IBM
Company.
Other product and service names might be trademarks of IBM or other companies.

© Copyright IBM Corp. 2018, 2019 xiv

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Course description

pref

Course description
Artificial Intelligence Analyst 2019

Duration: 5 days

Purpose
The Artificial Intelligence Analyst career path prepares students to apply AI concepts to build
real-life solutions. This career path introduces students to basic concepts of AI, machine learning
algorithms, natural language processing, chatbots, and computer vision. Students apply the
concepts they learn to practical examples by using IBM Watson services and tools on IBM Cloud.

Audience
Undergraduate senior students from IT related academic programs, for example, computer
science, software engineering, information systems and others.

Prerequisites
Before attending Module III AI Analyst classroom, students must meet the following prerequisites:
• Successful completion of Module I AI Overview (self-study).
• Successful completion of Module II Prerequisites (self-study).
• Successful completion of Exercise 0, Setting up your hands-on environment.

© Copyright IBM Corp. 2018, 2019 xv

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Course description

pref
Objectives
After completing this course, you should be able to:
• Explain what AI is.
• Describe the field of AI and its subfields: Machine learning, natural language processing (NLP),
and computer vision.
• List applications of AI in the industry and government.
• Describe machine learning.
• Describe different type of machine learning algorithms.
• Apply machine learning algorithms to specific problems.
• Explain deep learning.
• Explain convolutional neural networks and neural networks.
• Describe examples of unsupervised and supervised learning.
• Describe IBM Watson.
• Explain how Watson technology is applied to solve real world problems.
• Explain the capabilities of each Watson service.
• Describe Watson Studio, its components, and key applications.
• Describe the CRISP-DM process model and explain where machine learning fits in the
CRISP-DM process.
• Create machine learning models for different machine learning algorithms by using Watson
Studio.
• Explain domain adaptation.
• Describe the purpose of training the various Watson services.
• Describe IBM Watson Knowledge Studio capabilities and use.
• Explain what NLP is.
• List tools and services for NLP.
• Identify NLP use cases.
• Explain main NLP concepts.
• Explain how to evaluate the quality of an NLP algorithm.
• Identify the Watson services based on NLP technology.
• Use IBM Watson Discovery to build a cognitive query application.
• Describe chatbot applications and chatbots design guidelines.
• Explain core concepts and artifacts needed to build a chatbot application.
• Build chatbot applications with Watson Assistant and Node-RED.
• Explain what computer vision is.
• Identify computer vision use cases.
• Explain how computer vision analyzes and processes images and describe commonly used
computer vision techniques.
• Use the Watson Visual Recognition service to classify an image, detect faces, and recognize
text in an image.
• Create custom models with Watson Visual Recognition.
• Train the Watson Visual Recognition service with Watson Studio.
• Integrate multiple Watson services to build a comprehensive intelligent solution.

© Copyright IBM Corp. 2018, 2019 xvi

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Agenda

pref

Agenda

Note

The following unit and exercise durations are estimates, and might not reflect every class
experience.
The exercise durations do not include the optional parts or sections.
Students in this course use an IBM Cloud Lite account to perform the exercises. This account will
never expire, therefore students can continue working on the optional exercises after the class.

Day 1
(00:30) Welcome
(01:15) Unit 1 - Introduction to machine learning
(01:00) Exercise 1 - Applying machine learning algorithms
(01:00) Lunch break
(01:00) Unit 2 - Introduction to IBM Watson
(01:15) Exercise 2 - Exploring Watson services

Day 2
(00:30) Unit 3 - Introduction to IBM Watson Studio
(01:30) Exercise 3 - Getting started with Watson Studio
(00:30) Unit 4 - Introduction to IBM Watson Machine Learning
(01:00) Lunch break
(02:00) Exercise 4 - Getting started with Watson Machine Learning
(01:00) Exercise 5 - Exploring Deep Learning and Neural Network Modeler with Watson Studio

Day 3
(00:30) Unit 5 - Introduction to natural language processing (NLP)
(00:30) Unit 6 - NLP concepts and components
(00:30) Unit 7 - NLP evaluation metrics
(00:30) Unit 8 - NLP and IBM Watson
(01:00) Lunch break
(01:30) Exercise 6 - Ingest, Convert, Enrich and Query with Watson Discovery Service
(00:45) Unit 9 - Introduction to IBM Watson Knowledge Studio
(01:30) Exercise 7 - Creating a machine learning model with Watson Knowledge Studio

© Copyright IBM Corp. 2018, 2019 xvii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3
Agenda

pref
Day 4
(00:30) Unit 10 - Introduction to chatbots
(01:00) Unit 11 - Introduction to IBM Watson Assistant
(00:45) Exercise 8 - Getting started with Watson Assistant
(01:30) Exercise 9 - Help Desk chatbot
(01:00) Lunch break
(00:30) Unit 12 - Introduction to computer vision
(00:30) Unit 13 - Computer vision fundamentals
(00:45) Unit 14 - IBM Watson Visual Recognition
(02:00) Exercise 10 - Classifying images with Watson Visual Recognition

Day 5
(00:45) Unit 15 - Designing and building an intelligent solution
(01:30) Exercise 11 - Creating a cognitive banking FAQ chatbot
(01:00) Exercise 12 - Integrating Watson Knowledge Studio with Discovery for the procurement
domain (optional)
(01:00) Lunch break
(01:30) Practice test

© Copyright IBM Corp. 2018, 2019 xviii

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Unit 1. Introduction to machine learning

Estimated time
01:15

Overview
This unit recaps the main topics in Module I, AI overview and provides a deeper view into complex
subjects, such as:
• Machine learning
• Machine learning algorithms
• Neural networks
• Deep learning

© Copyright IBM Corp. 2018, 2019 1-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Unit objectives
• Explain what is machine learning.
• Describe what is meant by statistical model and algorithm.
• Describe data and data types.
• Describe machine learning types and approaches (Supervised,
Unsupervised and Reinforcement).
• List different machine learning algorithms.
• Explain what neural networks and deep learning are, and why they are
important in today’s AI field.
• Describe machine learning components.
• List the steps in the process to build machine learning applications.
• Explain what domain adaptation is and its applications.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 1-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
1.1. What is machine learning?

© Copyright IBM Corp. 2018, 2019 1-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

What is machine learning?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-2. What is machine learning?

© Copyright IBM Corp. 2018, 2019 1-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Topics

• What is machine learning?

• Machine learning algorithms
• What are neural networks?
• What is deep learning?
• How to evaluate a machine learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-3. Topics

© Copyright IBM Corp. 2018, 2019 1-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning

• In 1959, the term “machine learning” was first introduced by Arthur

Samuel. He defined it as the “field of study that gives computers the
ability to learn without being explicitly programmed”.
• The learning process improves the machine model over time by using
training data.
• The evolved model is used to make future predictions.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-4. Machine learning

Arthur Samuel, former IBM engineer and a professor at Stanford, was one of the pioneers in the
field of computer gaming and artificial intelligence. He was the first one to introduce the term
“machine learning”. Machine learning is a field of artificial intelligence. It uses statistical methods to
give computer the ability to "learn" from data, without being explicitly programmed.
If a computer program can improve how it performs certain tasks based on past experiences, then
it has learned. This differs from performing the task always the same way because it has been
programmed to do so.
The learning process improves the so-called “model” over time by using different data points
(training data). The evolved model is used to make future predictions.
References:
https://link.springer.com/chapter/10.1007/978-1-4302-5990-9_1
https://link.springer.com/chapter/10.1007/978-94-009-0279-4_9

© Copyright IBM Corp. 2018, 2019 1-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

What is a statistical model

• A model in a computer is a mathematical function that represents a

relationship or mapping between a set of inputs and a set of outputs.

• New data “X” can predict the output “Y”.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-5. What is a statistical model

The representation of a model in the computer is in the form of a mathematical function. It is a

relationship or mapping between a set of inputs and a set of outputs. For example, f(x)=x^2.
Assume that a system is fed with data indicating that the rates of violent crime are higher when the
weather is warmer and more pleasant, even rising sharply during warmer-than-typical winter days.
Then, this model can predict the crime rate for this year compared to last year’s rates based on the
weather forecast.
Returning to the mathematical representation of the model that can predict crime rate based on
temperature, we might propose the following mathematical model:
Violent crime incidents per day = Average Temperature × 2
This is an oversimplified example to explain that machine learning refers to a set of techniques for
estimating functions (for example, predicting crime incidents) that is based on data sets (pairs of the
day’s average temperature and the associated number of crime incidents). These models can be
used for predictions of future data.

© Copyright IBM Corp. 2018, 2019 1-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
1.2. Machine learning algorithms

© Copyright IBM Corp. 2018, 2019 1-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning algorithms

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-6. Machine learning algorithms

© Copyright IBM Corp. 2018, 2019 1-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Topics
• What is machine learning?
• Machine learning algorithms
• What are neural networks?
• What is deep learning?
• How to evaluate a machine learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-7. Topics

© Copyright IBM Corp. 2018, 2019 1-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning algorithms

• The machine learning algorithm is a technique through which the

system extracts useful patterns from historical data. These patterns
can be applied to new data.
• The objective is to have the system learn a specific input/output
transformation.
• The data quality is critical to the accuracy of the machine learning
results.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-8. Machine learning algorithms

To estimate the function that represents the model, an appropriate learning algorithm must be used.
In this context, the learning algorithm represents the technique through which the system extracts
useful patterns from the input historical data. These patterns can be applied to new data in new
situations. The objective is to have the system learn a specific input/output transformation and to
make future predictions for a new data point. Finding the appropriate algorithms to solve complex
problems in various domains and knowing how and when to apply them is an important skill that
machine learning engineers should acquire. Because the machine learning algorithms depend on
data, understanding and acquiring data with high quality is crucial for accurate results.

© Copyright IBM Corp. 2018, 2019 1-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning approaches

1) Supervised learning: Train by using labeled data, and learn and
predict new labels for unseen input data.
• Classification is the task of predicting a discrete class label, such as
“black, white, or gray” and “tumor or not tumor”.
• Regression is the task of predicting a continuous quantity, such as
“weight”, “probability”, and “cost”.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-9. Machine learning approaches

Supervised learning is one of the main categories of machine learning. In supervised machine
learning, input data (also known as training examples) comes with a label, and the goal of learning
is to predict the label for new, unforeseen examples. A supervised learning algorithm analyzes the
training data and produces an inferred function, which can be used for mapping new examples.
In practice, the problems that are solved by using supervised learning are grouped into either
regression or classification problems.
Classification is the task of predicting a discrete class label, such as “black, white, or gray” and
“tumor or not tumor”.
Regression is the task of predicting a continuous quantity, such as “weight”, “probability” and “cost”.

© Copyright IBM Corp. 2018, 2019 1-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning approaches (cont.)

2) Unsupervised learning: Detect patterns and relationships between
data without using labeled data.
• Clustering algorithms: Discover how to split the data set into a
number of groups such that the data points in the same groups are
more similar to each other compared to data points in other groups.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-10. Machine learning approaches (cont.)

Unsupervised learning is a machine learning type that learns from data that has not been labeled.
The goal of unsupervised learning is to detect patterns in the data. One of the most popular types of
unsupervised learning is clustering algorithms.
Clustering algorithms are algorithms that discover how to split the data set into a number of groups
such that the data points in the same groups are more similar to each other compared to data
points in other groups.

© Copyright IBM Corp. 2018, 2019 1-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning approaches (cont.)

3) Semi-supervised learning:
• A machine learning technique that falls between supervised and
unsupervised learning.
• It includes some labeled data with a large amount of unlabeled data.
• Here is an example that uses pseudo-labeling:
a. Use labeled data to train a model.
b. Use the model to predict labels for the unlabeled data.
c. Use the labeled data and the newly generated labeled data to create a
new model.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-11. Machine learning approaches (cont.)

Many real practical problems fall into this category of machine learning where you have little
labeled data and the rest of the data is unlabeled.
Labeling data is an expensive or time-consuming process. In addition, it mandates having domain
experts to label data accurately. Think about labeling skin diseases images that must be labeled by
a domain expert. Also, too much labeling data might introduce human biases into the model.
In semi-supervised learning, you try to get the best out of your unlabeled data. There are different
techniques to achieve this task. For example, you can use pseudo-labeling, which aims to give
approximate labels to unlabeled data. Pseudo-labeling works as follows:
1. Use labeled data to train a model.
2. Use the model to predict labels for the unlabeled data.
3. Use the labeled data and the newly generated labeled data to create a model.
References:
http://deeplearning.net/wp-content/uploads/2013/03/pseudo_label_final.pdf
https://www.analyticsvidhya.com/blog/2017/09/pseudo-labelling-semi-supervised-learning-techniqu
e/

© Copyright IBM Corp. 2018, 2019 1-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning approaches (cont.)

4) Reinforcement learning
• Reinforcement learning uses trial and error (a rewarding approach).
• The algorithm discovers an association between the goal and the
sequence of events that leads to a successful outcome.
• Example reinforcement learning applications:
ƒ Robotics: A robot that must find its way.
ƒ Self-driving cars.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-12. Machine learning approaches (cont.)

Reinforcement learning is a goal-oriented learning that is based on interaction with the

environment. As the system performs certain actions, it finds out more about the world.
Reinforcement learns through trial and error (a rewarding approach).
The algorithm discovers an association between the goal and the sequence of events that leads to
a successful outcome.
Example reinforcement learning problems:
• Robotics: A robot that must find its way.
• Self-driving cars.

© Copyright IBM Corp. 2018, 2019 1-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Machine learning algorithms

Understanding your problem and the different types of ML algorithms
helps in selecting the best algorithm.
Here are some machine learning algorithms:
• Naïve Bayes classification (supervised classification – probabilistic)
• Linear regression (supervised regression)
• Logistic regression (supervised classification)
• Support vector machine (SVM) (supervised linear or non-linear
classification)
• Decision tree (supervised non-linear classification)
• K-means clustering (unsupervised learning)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-13. Machine learning algorithms

In the following slides, we explore different machine learning algorithms. We describe the most
prominent algorithms. Each algorithm belongs to a category of learning. We explore supervised
and unsupervised algorithms, regression and classification algorithms, and linear and non-linear
classification.

© Copyright IBM Corp. 2018, 2019 1-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification

• Naïve Bayes classifiers assume that the value of a particular feature is
independent of the value of any other feature, given the class variable.
ƒ For example, a fruit may be considered to be an apple if it is red, round, and
about 10 cm in diameter.
ƒ Features: Color, roundness, and diameter.
ƒ Assumption: Each of these features contributes independently to the
probability that this fruit is an apple, regardless of any possible correlations
between the color, roundness, and diameter features.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-14. Naïve Bayes classification

Naïve Bayes classifiers is a powerful and simple supervised machine learning algorithm. It
assumes that the value of a particular feature is independent of the value of any other feature,
given the class variable. For example, a fruit may be considered to be an apple if it is red, round,
and about 10 cm in diameter.
Features: Color, roundness, and diameter.
A Naïve Bayes classifier considers each of these features to contribute independently to the
probability that this fruit is an apple, regardless of any possible correlations between the color,
roundness, and diameter features.

© Copyright IBM Corp. 2018, 2019 1-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

Example: Use Naïve Bayes to predict whether the Red, Round shaped,
10 cm diameter label is an apple or not.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-15. Naïve Bayes classification (cont.)

Imagine that you have the data set that is shown in the table in this slide. The column with title “Is
Apple?” represents the label of the data. Our objective is to make a new prediction for an unknown
object. The unknown object has the following features:
• Color: Red
• Shape: Round
• Diameter: 10 cm
Note 1: Sometimes the terminology “parameters” or “variables” is used to describe the “features”.
Note 2: “Annotated data” or “labeled data” refer to the same terminology.

© Copyright IBM Corp. 2018, 2019 1-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

To do a classification, you must perform the following steps:

1. Define two classes (CY and CN) that correspond to Apple = Yes and
Apple = No.

2. Compute the probability for CY as x: p(CY | x):

p(Apple = Yes | Colour = Red, Shape = round, Diameter => 10 cm)

3. Compute the probability for CN as x: p(CN | x):

p(Apple = No | Colour = Red, Shape = round, Diameter => 10 cm)

4. Discover which conditional probability is larger:

If p(CY |x) > p(CN |x), then it is an apple.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-16. Naïve Bayes classification (cont.)

Your algorithm basically depends on calculating two probability values:

• Class probabilities: The probabilities of having each class in the training data set.
• Conditional probabilities: The probabilities of each input feature giving a specific class value.
The process for solving this problem is as follows:
1. Define two classes CY and CN that correspond to Apple = Yes and Apple = No.
2. Compute the probability for CY as x: p(CY | x): p(Apple = Yes | Colour = Red, Shape = round,
Diameter => 10 cm)
3. Compute the probability for CN as x: p(CN | x): p(Apple = No | Colour = Red, Shape = round,
Diameter => 10 cm)
4. Discover which conditional probability is larger: If p(CY |x) > p(CN |x), then it is an apple.

© Copyright IBM Corp. 2018, 2019 1-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

Naïve Bayes model:

5. Compute p(x|CY) = p(Colour = Red, Shape = round, Diameter =>10

cm | Apple = Yes).

Naïve Bayes assumes that the features of the input data (the apple

parameters) are independent.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-17. Naïve Bayes classification (cont.)

The Naïve Bayes formula is given by this model. Our target is to compute the formula to reach
p(CK |x), where K is any class (CY or CN).
5. Compute the conditional probability of having each feature given that the class is CY: p(x|CY) =
p(Colour = Red, Shape = round, Diameter =>10 cm | Apple = Yes).
Because Naïve Bayes assumes that the features of the input data (the object features) are
independent, to get the p(x|CY) value, we calculate the conditional probability of each feature at a
time with the class CY, and then multiply all the values.

© Copyright IBM Corp. 2018, 2019 1-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

Thus, we can rewrite p(x| CY) as:

= p(Colour = Red | Apple = Yes) X p(Shape = round | Apple = Yes) X

p(Diameter => 10 cm | Apple = Yes)

Same for p(x| CN):

= p(Color = Red | Apple = No) X p(Shape = round | Apple = No) X

p(Diameter => 10 cm | Apple = No)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-18. Naïve Bayes classification (cont.)

Thus, we can rewrite p(x| CY) as:

= p(Colour = Red | Apple = Yes) X p(Shape = round | Apple = Yes) X p(Diameter => 10 cm | Apple
= Yes)
We apply the same rule for p(x| CN) by multiplying the conditional probabilities of reach input
feature given CN:
= p(Color = Red | Apple = No) X p(Shape = round | Apple = No) X p(Diameter => 10 cm | Apple =
No)

© Copyright IBM Corp. 2018, 2019 1-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

6. Calculate each conditional probability:
p(Colour = Red | Apple = Yes) = 3/5 (Out of five apples, three of them were red.)
p(Colour = Red | Apple = No) = 2/5
p(Shape = Round | Apple = Yes) = 4/5
p(Shape = Round | Apple = No) = 2/5
p(Diameter = > 10 cm | Apple = Yes) = 2/5
p(Diameter = > 10 cm | Apple = No) = 3/5

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-19. Naïve Bayes classification (cont.)

Let us see how to calculate these conditional probabilities. For example, to calculate p(Colour =
Red | Apple = Yes), you are asking, “What is the probability for having a red color object given that
we know that it is an apple”.
You browse the table to see how many “is Apple?” has a “yes” label. You see that the occurrence is
five times.
Now, from the table, how many of these five occurrences are when you have a color = red? You find
that there are three occurrences for red color. Therefore, p(Colour = Red | Apple = Yes) = 3/5.
Repeat these steps for the rest of the features.

© Copyright IBM Corp. 2018, 2019 1-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

• p(Color = Red | Apple = Yes) X p(Shape = round | Apple = Yes) X

p(Diameter = > 10 cm | Apple = Yes)

= (3/5) x (4/5) x (2/5) = 0.192

• p(Color = Red | Apple = No) X p(Shape = round | Apple = No) X

p(Diameter = > 10 cm | Apple = No)

= (2/5) x (2/5) x (3/5) = 0.096

• p(Apple = Yes) = 5/10

• p(Apple = No) = 5/10

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-20. Naïve Bayes classification (cont.)

Now, we have all the values that we need. As mentioned in step 5, we multiply the conditional
probabilities as follows:
p(Color = Red | Apple = Yes) X p(Shape = round | Apple = Yes) X p(Diameter = > 10 cm | Apple =
Yes)
= (3/5) x (4/5) x (2/5) = 0.192
p(Color = Red | Apple = No)p(Shape = round | Apple = No)p(Diameter = > 10 cm | Apple = No)
= (2/5) x (2/5) x (3/5) = 0.096
p(Apple = Yes) = 5/10
p(Apple = No) = 5/10

© Copyright IBM Corp. 2018, 2019 1-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Naïve Bayes classification (cont.)

Compare p(CY | x) to p(CN | x):

Therefore, the verdict is that it is an apple.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-21. Naïve Bayes classification (cont.)

Finally, we compare the values of p(CY |x) versus p(CN |x). By substituting the values that were
calculated in the previous steps, we discover that p(CY |x) > p(CN |x), which means that the object
is an apple.

© Copyright IBM Corp. 2018, 2019 1-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression
• Linear regression is a linear equation that combines a specific set of
input values (X) and an outcome (Y) that is the predicted output for that
set of input values. As such, both the input and output values are
numeric.
• The target variable is a continuous value.
Examples for applications:
• Analyze the marketing effectiveness, pricing, and promotions on the
sales of a product.
• Forecast sales by analyzing the monthly company’s sales for the past
few years.
• Predict house prices with an increase in the sizes of houses.
• Calculate causal relationships between parameters in biological
systems.
Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-22. Linear regression

Regression algorithms are one of the key algorithms that are used in machine learning. Regression
algorithms help analysts to model relationships between input variables X and the output label Y for
the training data points. This algorithm targets supervised regression problems, that is, the target
variable is a continuous value.
In simple linear regression, we establish a relationship between the target variable and input
variables by fitting a line that is known as the regression line.
There are different applications that benefit from linear regression:
• Analyze the marketing effectiveness, pricing, and promotions on the sales of a product.
• Forecast sales by analyzing the monthly company’s sales for the past few years.
• Predict house prices with an increase in the sizes of houses.
• Calculate causal relationships between parameters in biological systems.

© Copyright IBM Corp. 2018, 2019 1-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• Example: Assume that we are studying the real state market.
• Objective: Predict the price of a house given its size by using previous
data.
Size Price

30 30,000

70 40,000

90 55,000

110 60,000

130 80,000

150 90,000

180 95,000

190 110,000

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-23. Linear regression (cont.)

Assume that we are studying the real state market and our objective is to predict the price of a
house given its size by using previous data. The label in this case is the price column.

© Copyright IBM Corp. 2018, 2019 1-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

Plot this data as a graph

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-24. Linear regression (cont.)

After plotting the points on the graph, they seem to be forming a line.

© Copyright IBM Corp. 2018, 2019 1-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• Can you guess what is the best estimate for a price of a 140-meter
square house?
• Which one is correct?
A. $60,000
Size Price
B. $95,000 30 30,000
C. $85,000
70 40,000

90 55,000

110 60,000

130 80,000

150 90,000

180 95,000

190 110,000

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-25. Linear regression (cont.)

You want to find the price value of a 140-meter square house. Which of the following choices is
correct?
1. $60,000
2. $95,000
3. $85,000

© Copyright IBM Corp. 2018, 2019 1-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• Target: A line that is within a “proper” distance from all points.
• Error: The aggregated distance between data points and the assumed
line.
• Solution: Calculate the error iteratively until you reach the most
accurate line with a minimum error value (that is, the minimum distance
between the line and all points).

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-26. Linear regression (cont.)

To answer the question “What is the price for a 140-meter square house?”, we need to draw the line
that best fits most of the data points.
How we can find the line that best fits all the data points? We can draw many lines, so which one is
the best line?
The best line should have the minimal error value. The error refers to the aggregated distance
between data points and the assumed line. Calculate the error iteratively until you reach the most
accurate line with a minimum error value.

© Copyright IBM Corp. 2018, 2019 1-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• After the learning process, you get the most accurate line, the bias, and the
slope to draw your line.

• Here is our linear regression model representation for this problem:

h(p) = p0 + p1 * X1
or
Price = 30,000 + 392* Size
Price = 30,000 + 392* 140
= 85,000

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-27. Linear regression (cont.)

After the learning process, you get the most accurate line, the bias, and the slope to draw your line.
p0 is the bias. It is also called the intercept because it determines where the line intercepts the y
axis.
p1 is the slope because it defines the slope of the line or how x correlates with a y value before
adding the bias.
If you have the optimum value of p0 and p1 , you can draw the line that best represents the data.

© Copyright IBM Corp. 2018, 2019 1-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• Squared error function Æ

ƒ m is the number of samples.
ƒ is the predicted value for data point i.
ƒ is the actual value for data point i.
Target: Choose P values to minimize errors.
• Stochastic Gradient descent algorithm:

j is the feature number.

is the learning rate.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-28. Linear regression (cont.)

The squared error function J is represented by the difference between the predicted point and the
actual points. It is calculated as follows:
J(P) = (1/(2*m)) Σ (hp (xi ) - yi)2
Where:
• i is the number of a sample or data point within the data set samples.
• hp (xi ) is the predicted value for data point i.
• yi is the actual value for data point i.
• m is the count of data set samples or data points.
We can use an optimization technique that is called stochastic gradient descent. The algorithm
evaluates and updates the weights on every iteration to minimize the model error. The technique
works iteratively. In each iteration, the training instance is exposed to the model once. The model
makes a prediction and the corresponding error is calculated. The model is updated to reduce the
error for the next prediction. The process continues to adjust the model weights to reach the
smallest error.

© Copyright IBM Corp. 2018, 2019 1-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
Here we use the gradient descent algorithm to iteratively get the values of p0 and p1 (the intercept
and slope of the line are also called weights) by the following algorithm:
Pj := Pj – α (hp (xi ) - yi) xj i
Where:
j is the feature number.
α is the learning rate.

© Copyright IBM Corp. 2018, 2019 1-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Linear regression (cont.)

• In higher dimensions where we have more than one input (X), the line is
called a plane or a hyper-plane.
• The equation can be generalized from simple linear regression to
multiple linear regression as follows:
Y(X)=p0+p1*X1+p2*X2+...+pn*Xn

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-29. Linear regression (cont.)

With more features, you do not have a line; instead, you have a plane. In higher dimensions where
we have more than one input (X), the line is called a plane or a hyper-plane.
The equation can be generalized from simple linear regression to multiple linear regression as
follows:
Y(X)=p0+p1*X1+p2*X2+...+pn*Xn

© Copyright IBM Corp. 2018, 2019 1-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Logistic regression
• Supervised classification algorithm.
• Target: A dependent variable (Y) is a discrete category or a class (not a
continuous variable as in linear regression).
Example: Class1 = Cancer, Class2 = No Cancer

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-30. Logistic regression

Logistic regression is a supervised classification algorithm. It is different from linear regression

where the dependent or output variable is a category or class. The target is a discrete category or a
class (not a continuous variable as in linear regression), for example, Class1 = cancer, Class2 = No
Cancer.

© Copyright IBM Corp. 2018, 2019 1-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Logistic regression (cont.)

• Logistic regression is named for the function that is used at the core of
the algorithm.
• The logistic function (sigmoid function) is an S-shaped curve for data
discrimination across multiple classes. It can take any real value 0 – 1.

Logistic function

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-31. Logistic regression (cont.)

Logistic regression is named for the function that is used at the core of the algorithm, which is the
logistic function. The logistic function is also known as the sigmoid function. It is an S-shaped curve
(as shown in the figure) for data segregation across multiple classes that can take any real value 0
- 1.

© Copyright IBM Corp. 2018, 2019 1-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Logistic regression (cont.)

• The sigmoid function squeezes the input value between [0,1].

• Logistic regression equation:
Y = exp(p0+p1X)/(1+exp(p0+p1X))

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-32. Logistic regression (cont.)

During the learning process, the system tries to generate a model (estimate a set of parameters p0,
p1, …) that can best predict the probability that Y will fall in class A or B given the input X. The
sigmoid function squeezes the input value between [0,1], so if the output is 0.77 it is closer to 1, and
the predicted class is 1.

© Copyright IBM Corp. 2018, 2019 1-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Logistic regression (cont.)

• Example: Assume that the estimated values of p’s for a certain model
that predicts the gender from a person’s height are p0= -120 and p1 =
0.5.
• Class 0 represents female and class 1 represents male.
• To compute the prediction, use:
Y = exp(-120+0.5X)/(1+exp(-120+0.5X))
Y = 0.00004539
P(male|height=150) is 0 in this case.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-33. Logistic regression (cont.)

Example: Assume that the estimated values of p’s for a certain model that predicts the gender from
a person’s height are p0= -120 and p1=0.5.
Assume that you have two classes where class 0 represents female and class 1 represents male.
Y = exp(-120+0.5X)/(1+exp(-120+0.5X))
Y = 0.00004539
P(male|height=150) is 0 in this case.

© Copyright IBM Corp. 2018, 2019 1-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Support vector machine

• The goal is to find a separating hyperplane between positive and
negative examples of input data.
• SVM is also called a “large Margin Classifier”.
• The SVM algorithm seeks the hyperplane with the largest margin, that
is, the largest distance to the nearest sample points.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-34. Support vector machine

SVM is a supervised learning model that can be a linear or non-linear classifier. SVM is also called
a “large Margin Classifier” because the algorithm seeks the hyperplane with the largest margin, that
is, the largest distance to the nearest sample points.

© Copyright IBM Corp. 2018, 2019 1-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Support vector machine (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-35. Support vector machine (cont.)

Assume that a data set lies in a two-dimensional space and that the hyperplane will be a
one-dimensional line.
Although many lines (in light blue) do separate all instances correctly, there is only one optimal
hyperplane (red line) that maximizes the distance to the closest points (in yellow).

© Copyright IBM Corp. 2018, 2019 1-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree
• A supervised learning algorithm that uses a tree structure to model
decisions.
• It resembles a flow-chart or if-else cases.
• An example for applications is general business decision-making like
predicting customers’ willingness to purchase a given product in a
given setting, for example, online versus a physical store.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-36. Decision tree

A decision tree is a popular supervised learning algorithm that can be used for classification and
regression problems. Decision trees are a popular prediction method. Decision trees can explain
why a specific prediction was made by traversing the tree.
There are different examples for applications that can use decision tree in business. For example,
predicting customers’ willingness to purchase a given product in a given setting, for example, online
versus a physical store.

Note

In our scope, we focus on a classification tree.

© Copyright IBM Corp. 2018, 2019 1-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-37. Decision tree (cont.)

A decision tree includes three main entities: root node, decision nodes, and leaves. The figure
shows the graphical representation of these entities.
A decision tree builds the classification or regression model in the form of a tree structure. It
resembles a flowchart, and is easy to interpret because it breaks down a data set into smaller and
smaller subsets while building the associated decision tree.

© Copyright IBM Corp. 2018, 2019 1-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-38. Decision tree (cont.)

The “Play Tennis” example is one of the most popular examples to explain decision trees.
In the data set, the label is represented by “PlayTennis”. The features are the rest of the columns:
“Outlook”, “Temperature”, “Humidity”, and “Wind”. Our goal here is to predict, based on some
weather conditions, whether a player can play tennis or not.
Reference:
http://jmvidal.cse.sc.edu/talks/decisiontrees/choosingbest.html?style=White

© Copyright IBM Corp. 2018, 2019 1-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-39. Decision tree (cont.)

Back to the example, the decision tree representation on the right side of the figure shows the
following information:
• Each internal node tests an attribute.
• Each branch corresponds to an attribute value.
• Each leaf node assigns a classification.
Eventually, we want to make a classification of “if Play Tennis = {Yes, No}”.
Reference:
http://jmvidal.cse.sc.edu/talks/decisiontrees/choosingbest.html?style=White

© Copyright IBM Corp. 2018, 2019 1-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree (cont.)

A decision tree is built by making decisions regarding the following
items:
• Which feature to choose as the root node
• What conditions to use for splitting
• When to stop splitting

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-40. Decision tree (cont.)

The algorithm works by recursively splitting the data based on the value of a feature. After each
split, the portion of the data becomes more homogeneous.
Now, the algorithm needs to decide:
1. Which feature to choose as the root node.
2. What conditions to use for splitting.
3. When to stop splitting.

© Copyright IBM Corp. 2018, 2019 1-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Decision tree (cont.)

• Using entropy and information gain to construct a decision tree.
• Entropy: It is the measure of the amount of uncertainty and
randomness in a set of data for the classification task.
• Information gain: It is used for ranking the attributes or features to
split at given node in the tree.
Information gain = (Entropy of distribution before the split)–(entropy of
distribution after it)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-41. Decision tree (cont.)

The Iterative Dichotomiser3 (ID3) algorithm works by using entropy and information gain to
construct a decision tree. Entropy is the measure of the amount of uncertainty and randomness in a
set of data for the classification task. Entropy is maximized when all points have equal probabilities.
If entropy is minimal, it means that the attribute or feature appears close to one class and has a
good discriminatory power for classification.
Entropy zero means that there is no randomness for this attribute.
Information gain is a metric that is used for ranking the attributes or features to split at given node in
the tree. It defines how much information a feature provides about a class. The feature with the
highest information gain is used for the first split.

© Copyright IBM Corp. 2018, 2019 1-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-mean clustering
• Unsupervised machine learning algorithm.
• It groups a set of objects in such a way that objects in the same group
(called a cluster) are more similar to each other than those in other
groups (other clusters).

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-42. K-mean clustering

K-means clustering is an unsupervised machine learning technique. The main goal of the algorithm
is to group the data observations into k clusters, where each observation belongs to the cluster with
the nearest mean.
A cluster’s center is the centroid. The figure shown plots of the partition of a data set into five
clusters, with the cluster centroids shown as crosses.

© Copyright IBM Corp. 2018, 2019 1-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

Examples for applications include customer segmentation, image
segmentation, and recommendation systems.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-43. K-means clustering (cont.)

Examples of applications include:

• Customer segmentation: Imagine that you are the owner of electronics store. You want to
understand preferences of your clients to expand your business. It is not possible to look at
each client’s purchase details to find a good marketing strategy. But, you can group the details
into, for example, five groups based on their purchasing habits. Then, you start building your
marketing strategy for each group.
• Image segmentation and compression: The process of partitioning a digital image into multiple
segments (sets of pixels) to simplify and change the representation of an image into something
that is more meaningful and easier to analyze. To achieve this task, we need a process that
assigns a label to every pixel in an image such that pixels with the same label share certain
features. The image in this slide is segmented and compressed into three regions by using
k-means clustering. With smaller number of clusters, it provides more image compression but at
the expense of less image quality.
• Recommendation systems: These systems help you find users with the same preferences to
build better recommendation systems.

© Copyright IBM Corp. 2018, 2019 1-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
References:
https://www.mathworks.com/help/examples/images/win64/SegmentGrayscaleImageUsingKMeans
ClusteringExample_02.png
https://www.mathworks.com/help/examples/images/win64/SegmentGrayscaleImageUsingKMeans
ClusteringExample_01.png

© Copyright IBM Corp. 2018, 2019 1-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

• Example: Given the following data points, use K-means clustering to
partition data into two clusters.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-44. K-means clustering (cont.)

Assume that you have the data points that are show in the figure. Your goal is to cluster each data
point into one of two groups. Thus, the cluster size is 2. C1 and C2 represent these two clusters.

© Copyright IBM Corp. 2018, 2019 1-49

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

• Set initial centroids are C1 (1,1) and C2 (2,1)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-45. K-means clustering (cont.)

Assume initial centroids are C1, point (1,1) and C2, point (2,1)

© Copyright IBM Corp. 2018, 2019 1-50

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

Find a new centroid by usingÆ

Iteration 1:
• Now, we calculate for each point to which center it belongs. The result
depends on the distance between the center and the point (by using
Euclidian distance):
Point 1: (1, 1) Æ d11 = Yes d12 = No
This means point1(2,2) belongs to C1 and not C2 because it is closer to C1.
ƒ Point 2: (2, 1) Æ d21 = No, d22 = Yes
ƒ Point 3: (4, 3) Æ d31 = No, d32 = Yes
ƒ Point 4: (5, 4) Æ d41 = No, d42 = Yes

• Now, we calculate the new centroid as follows:

ƒ C1 = (1, 1)
ƒ C2 = 1/3 ((2, 1) + (4, 3) + (5, 4)) = (3.67, 2.67)
Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-46. K-means clustering (cont.)

To compute the centroid of a cluster, use an iterative process where each point is examined and
you determine whether it belongs to a specific cluster. Then, you compute the new centroid by
using the mean of all points.

© Copyright IBM Corp. 2018, 2019 1-51

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-47. K-means clustering (cont.)

As you see, the new points in red are the new centroids. We apply another iteration to find a better
centroid that represents each cluster.

© Copyright IBM Corp. 2018, 2019 1-52

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

Iteration 2:
• Point 1: (1, 1) Æ d11 = Yes, d12 = No
• Point 2: (2, 1) Æ d21 = Yes, d22 = No
• Point 3: (4, 3) Æ d31 = No, d32 = Yes
• Point 4: (5, 4) Æ d41 = No, d42 = Yes
Now, we calculate the new centroid as follows:
• C1 = 1/2 ((1, 1)+(2,1)) = (1.5,1)
• C2 = 1/2 ((4, 3) + (5, 4)) = (4,5, 3.5)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-48. K-means clustering (cont.)

Now, we examine each point again against the centroid by using Euclidian distance and calculate
the new centroids (C1 and C2).

© Copyright IBM Corp. 2018, 2019 1-53

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

K-means clustering (cont.)

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-49. K-means clustering (cont.)

As you see, the new red centroids represent the centers of the two clusters. The algorithm stops
when the centroids do not change or change slightly, or if a maximum number of iterations are
defined.

© Copyright IBM Corp. 2018, 2019 1-54

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
1.3. What are neural networks?

© Copyright IBM Corp. 2018, 2019 1-55

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

What are neural networks?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-50. What are neural networks?

© Copyright IBM Corp. 2018, 2019 1-56

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Topics
What is machine learning?
Machine learning algorithms
What are neural networks?
What is deep learning?
How to evaluate a machine learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-51. Topics

© Copyright IBM Corp. 2018, 2019 1-57

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Neural networks
• Machine learning models that are inspired by the structure of the human
brain.
• The human brain is estimated to have 100 billion neurons, and each
neuron is connected to up to 10,000 other neurons.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-52. Neural networks

Neural networks represent an information-processing paradigm that is inspired by the human brain.
In the brain, neurons are highly connected and communicate chemical signals through the
synapses (a junction between two nerve cells) between the axons and dendrites. The human brain
is estimated to have 100 billion neurons, with each neuron connected to up to 10,000 other
neurons.
The figure shows a representation of a network of neurons in the brain.

© Copyright IBM Corp. 2018, 2019 1-58

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Neural networks (cont.)

• Artificial neural networks are collections of interconnected “neurons”
(called nodes) that work together to transform input data to output data.
• Each node applies a mathematical transformation to the data it
receives; it then passes its result to the other nodes in its path.
• Examples for applications:
ƒ Object detection, tracking, and image and video analysis

ƒ Natural language processing (for example, machine translation)

ƒ Autonomous cars and robots

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-53. Neural networks (cont.)

Artificial neural networks communicate signals (numbers) through weights and activation functions
that activate neurons. Using a training algorithm, these networks adjust those weights to solve a
problem.
Each node applies a mathematical transformation to the data it receives; it then passes its result to
the other nodes in its path. Each connection between nodes represents a different parameter to the
model.
A neural network is useful for machine learning tasks that have too many features (millions). For
example:
• Object detection, tracking, and image and video analysis by using a Convolutional Neural
Network (CNN)
• Natural language processing tasks like speech recognition and machine translation by using a
recurrent neural network (RNN)
• Autonomous cars and robots (more complex neural networks)

© Copyright IBM Corp. 2018, 2019 1-59

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Neural networks (cont.)

• Three or more layers (an input layer, one or many hidden layers, and an
output layer).
• Neural network models can adjust and learn as data changes.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-54. Neural networks (cont.)

A neural network is composed of three or more layers: an input layer, one or many hidden layers,
and an output layer. Data is imported through the input layer. Then, the data is modified in the
hidden and output layers based on the weights that are applied to their nodes. The typical neural
network can consist of thousands or even millions of simple processing nodes that are densely
interconnected.

© Copyright IBM Corp. 2018, 2019 1-60

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Perceptron
• A single neuron model and originator for the neural network.
• Similar to linear classification, where each input has weight.
• One bias.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-55. Perceptron

A perceptron is a single neuron model that was an originator for neural networks. It is similar to
linear regression. Each neuron has its own bias and slope (weights). For example, assume that a
neuron have two inputs (X1 and X2 ), so it requires three weights (P1, P2 and P0 ). The figure in this
slide shows a weight for each input and one for the bias.

© Copyright IBM Corp. 2018, 2019 1-61

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Neural networks: Backpropagation

Backpropagation is an algorithm for training neural networks that has
many layers. It works in two phases:
• First phase: The propagation of inputs through a neural network to the
final layer (called feedforward).
• Second phase: The algorithm computes an error. An error value is
then calculated by using the wanted output and the actual output for
each output neuron in the network. The error value is propagated
backward through the weights of the network (adjusting the weights)
beginning with the output neurons through the hidden layer and to the
input layer (as a function of the contribution of the error).

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-56. Neural networks: Backpropagation

Backpropagation is an algorithm for training neural networks that have many layers. It works in two
phases:
• Propagation of inputs through a neural network to the final layer (called feedforward).
• The algorithm computes an error. An error value is then calculated by using the wanted output
and the actual output for each output neuron in the network. The error value is propagated
backward through the weights of the network (adjusting the weights) beginning with the output
neurons through the hidden layer and to the input layer (as a function of the contribution of the
error).
Backpropagation continues to be an important aspect of neural network learning. With faster and
cheaper computing resources, it continues to be applied to larger and denser networks.

© Copyright IBM Corp. 2018, 2019 1-62

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
1.4. What is deep learning?

© Copyright IBM Corp. 2018, 2019 1-63

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

What is deep learning?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-57. What is deep learning?

© Copyright IBM Corp. 2018, 2019 1-64

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Topics
• What is machine learning?
• Machine learning algorithms
• What are neural networks?
• What is deep learning?
• How to evaluate a machine learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-58. Topics

© Copyright IBM Corp. 2018, 2019 1-65

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Deep learning
• Similar to a traditional neural network, but it has many more hidden
layers.
• Deep learning has emerged now because of the following reasons:
ƒ Emergence of big data, which requires data processing scaling.
ƒ Improvement in processing power and the usage of GPUs to train neural
networks.
ƒ Advancement in algorithms like the rectified linear unit (ReLU).

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-59. Deep learning

Deep learning is a machine learning technique that uses neural networks to learn. Although deep
learning is similar to a traditional neural network, it has many more hidden layers. The more
complex the problem, the more hidden layers there are in the model.
Deep learning has emerged now because of the following reasons:
• The continuous increase in big data requires data processing scaling to analyze and use this
data correctly.
• Improvement in processing power and the usage of GPUs to train neural networks.
• Advancement in algorithms like the rectified linear unit (ReLU) instead of the Sigmoid algorithm
helps make gradient descent converge faster.

© Copyright IBM Corp. 2018, 2019 1-66

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Deep learning (cont.)

Applications:
• Multilayer perceptron (MLP): Classification and regression, for example, a
house price prediction.
• Convolutional neural network (CNN): For image processing like facial
recognition.
• Recurrent neural network (RNN): For one-dimensional sequence input
data. Like audio and languages.
• Hybrid neural network: Covering more complex neural networks, for
example, autonomous cars.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-60. Deep learning (cont.)

There are various types of neural networks. Each network is more suitable for a type of machine
learning problem. Here is an overview for these networks and their applications:
• Multilayer perceptron (MLP): A class of feed-forward artificial neural networks (ANNs). It is
useful in classification problems where inputs are assigned a class. It also works in regression
problems for a real-valued quantity like a house price prediction.
• Convolutional neural network (CNN): Takes an input as an image. It is useful for image
recognition problems like facial recognition.
• Recurrent neural network (RNN): Has a temporal nature where the input may be a function in
time, such as audio files. It is also used for one-dimensional sequence data. It is suitable for
inputs like audio and languages. It can be used in applications like speech recognition and
machine translation.
• Hybrid neural network: Covers more complex neural networks, for example, autonomous cars
that require processing images and work by using radar.
Reference:
https://machinelearningmastery.com/when-to-use-mlp-cnn-and-rnn-neural-networks/

© Copyright IBM Corp. 2018, 2019 1-67

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
1.5. How to evaluate a machine learning
model?

© Copyright IBM Corp. 2018, 2019 1-68

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

How to evaluate a machine

learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-61. How to evaluate a machine learning model?

© Copyright IBM Corp. 2018, 2019 1-69

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Topics
• What is machine learning?
• Machine learning algorithms
• What are neural networks?
• What is deep learning?
• How to evaluate a machine learning model?

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-62. Topics

© Copyright IBM Corp. 2018, 2019 1-70

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Model evaluation
• Overfitting occurs when a machine learning model can fit the training
set perfectly and fails with unseen future data.
ƒ Reason: Too many features are used or you are reusing training
samples in testing.
ƒ Solution:
í Fewer features
í More data
í Cross-validation

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-63. Model evaluation

After you have successfully trained your model, you need a methodology to follow to evaluate your
machine learning model performance. A classic mistake is to use the same sample data that is
used in training to test a model, which produces a false perfect score. This is called “overfitting”
(also referred as “high variance”). The problem with overfitting is that your model fails at predicting
future unseen data.
Another case that can cause overfitting is where you have unbalanced data. For example, assume
that you are working on a data set for churn analysis. The customers who churned are actually 2%
of your data set. Using this data set “as is” causes overfitting.
The objective of a good machine learning model is to generalize for any future data points.
Overfitting also can occur if you are using too many features. Relatively, if the number of features is
the same as or greater than the number of training samples, that can cause overfitting. One of the
solutions to overcome overfitting is to increase the number of data set samples that is used for
training compared to features. Another solution is to manually decrease the number of features, but
that might result in removing useful information. Another solution is to perform model selection by
using cross-validation.

© Copyright IBM Corp. 2018, 2019 1-71

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
References:
https://www.coursera.org/lecture/machine-learning/the-problem-of-overfitting-ACpTQ
https://en.oxforddictionaries.com/definition/overfitting
https://ai.stanford.edu/~ang/papers/cv-final.pdf
https://www.youtube.com/watch?v=OSd30QGMl88

© Copyright IBM Corp. 2018, 2019 1-72

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Model evaluation (cont.)

• Underfitting occurs when a machine learning model cannot fit the

training data or generalize to new data.
ƒ Reason: The model is using a simple estimator.
ƒ Solution: Add More features or use different estimator

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-64. Model evaluation (cont.)

Underfitting (also referred to as “high bias”) occurs when a machine learning model cannot fit the
training data or generalize to new data.
A possible reason might be that the model is using a simple estimator. For example, you might be
using a linear estimator, but what you actually need is a quadratic or higher degree polynomial
estimator to develop your model like in “Right fit” graph.
Another reason might be that you are not using enough features, so your estimator fails to capture
the structure of the data. A possible solution would be to add more features and try a different
estimator.
There are other methods that are used to help resolve the overfitting and underfitting of your model
such as regularization, but these methods are beyond the scope of this course.
References:
https://en.oxforddictionaries.com/definition/overfitting
https://www.youtube.com/watch?v=OSd30QGMl88

© Copyright IBM Corp. 2018, 2019 1-73

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Model evaluation (cont.)

• Cross-validation (CV) is a process to evaluate a model by dividing the
data set once or several times in training and testing.
• Hold-out method: Randomly splits the data set into a training set and
test set.
• K-fold cross validation: Splits data into K subsamples where each
subsample gets a chance to be the validation set, and K-1 is the
training set.
• Leave one out cross validation (LOO-CV): Similar to K-fold except
that one subsample that contains one data point is held out, and the
rest of data is used for training.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-65. Model evaluation (cont.)

It is common practice when applying a (supervised) machine learning task is to hold out part of the
available data as a test set. There are different methods to achieve that task:
• Cross-validation (CV) is a process to evaluate a machine learning model by splitting a data set
once or several times to train and test the model. The data set can be split into a training set to
train the model and a validation set to pre-test the model. Select the model that has least error.
Finally, there is a test set to evaluate the model. Thus, the data set can be split as 60% - 20% -
20% for training, validation, and testing sets.
One criticism of this process is that splitting the data set into three parts reduces the number of
samples that can be used for training the model.
• The hold-out method partitions the data set into a majority set for training and minority set for
testing. The split of the training set to test set is 80% - 20% or 70% - 30%, with no fixed rule.

© Copyright IBM Corp. 2018, 2019 1-74

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty
• K-fold cross validation randomly partitions data into K equal sized subsamples. For each
iteration, one subsample is kept as validation set and the rest of the subsamples (K-1) are the
training set. The iterations are repeated K times, where each subsample has one chance to be
the validation set. The K results can then be averaged to produce a single model. The biggest
advantage of K-fold is that all data is changed to be used for both training and validation. There
is no strict rule for the number K, but it is commonly K=5 or K=10, which are 5-fold
cross-validation or 10-fold cross-validation. For each subsample, you maintain approximately
the same percentage of data of each target class as in the complete set, which is known as the
Stratified K-fold method.
• Leave one out CV (LOO-CV) is similar to K-fold, but in this case each one sample data point is
held out as a validation set, and the rest of data set is the training set. Comparing LOO-CV and
K-fold, K-fold is faster and requires less computation, but in terms of accuracy, LOO-CV often
has a high variance as an estimator.
References:
https://projecteuclid.org/download/pdfview_1/euclid.ssu/1268143839
http://scikit-learn.org/stable/modules/cross_validation.html
https://www.cs.cmu.edu/~schneide/tut5/node42.html

© Copyright IBM Corp. 2018, 2019 1-75

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Unit summary
• Explain what is machine learning.
• Describe what is meant by statistical model and algorithm.
• Describe data and data types.
• Describe machine learning types and approaches (Supervised,
Unsupervised and Reinforcement).
• List different machine learning algorithms.
• Explain what neural networks and deep learning are, and why they are
important in today’s AI field.
• Describe machine learning components.
• List the steps in the process to build machine learning applications.
• Explain what domain adaptation is and its applications.
Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-66. Unit summary

© Copyright IBM Corp. 2018, 2019 1-76

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Review questions
1. True or False: In logistic regression, the target output is a
continuous value.
2. True or False: Autonomous cars are one of many
applications of deep learning.
3. What type of learning is K-means clustering?
A. Semi-supervised learning
B. Supervised learning
C. Unsupervised learning
D. None of the above

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-67. Review questions

1. False
2. True
3. C. Unsupervised learning

© Copyright IBM Corp. 2018, 2019 1-77

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Review questions (cont.)

4. Assume that you want to develop a learning algorithm to

address the following problem: You want to examine
individual customer accounts and determine whether they
have been hacked or compromised. This should be treated
as a supervised __________.
A. Classification
B. Regression

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-68. Review questions (cont.)

A. Classification

© Copyright IBM Corp. 2018, 2019 1-78

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Review answers
1. True or False: In a logistic regression, the target output is a
continuous value.
The answer is False.
2. True or False: Autonomous cars are one of many
applications of deep learning.
The answer is True.
3. What type of learning is K-means clustering?
A. Semi-supervised learning
B. Supervised learning
C. Unsupervised learning
D. None of the above
The answer is C.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-69. Review answers

© Copyright IBM Corp. 2018, 2019 1-79

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Review answers (cont.)

4. Assume that you want to develop a learning algorithm to

address the following problem: You want to examine
individual customer accounts and determine whether they
have been hacked or compromised. This should be treated
as a supervised ___________.
A. Classification
B. Regression
The answer is A.

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-70. Review answers (cont.)

© Copyright IBM Corp. 2018, 2019 1-80

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Exercise: Applying machine

learning algorithms

Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-71. Exercise: Applying machine learning algorithms

© Copyright IBM Corp. 2018, 2019 1-81

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 1. Introduction to machine learning

Uempty

Exercise objectives
• This exercise provides the foundational concepts that you
need to understand to apply four popular machine learning
algorithms:
ƒ K-means clustering
ƒ Naïve Bayes classifier
ƒ Linear regression
ƒ Decision tree

• After completing this exercise, you should be able to:

ƒ Determine the centroids of a data set with the K-means clustering
algorithm.
ƒ Predict the class of an object with the Naïve Bayes classifier.
ƒ Apply the linear regression algorithm to solve supervised learning
problems.
ƒ Construct a decision tree to predict outcomes.
Introduction to machine learning © Copyright IBM Corporation 2019

Figure 1-72. Exercise objectives

After completing this exercise, you should be able to:

• Determine the centroids of a data set with the K-means clustering algorithm.
• Predict the class of an object with the Naïve Bayes classifier.
• Apply the linear regression algorithm to solve supervised learning problems.
• Construct a decision tree to predict outcomes.

© Copyright IBM Corp. 2018, 2019 1-82

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Unit 2. Introduction to IBM Watson

Estimated time
01:00

Overview
This unit provides an overview of key IBM Watson services, their purpose, how they work, and it
helps you get started with Watson services on IBM Cloud.

© Copyright IBM Corp. 2018, 2019 2-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Unit objectives
• Explain what IBM Watson is.
• List the Watson service.
• Explain the capabilities of each Watson service.
• Describe the purpose of training the various Watson services to adapt
them to a closed-domain.
• List the Watson services that can be trained.
• List the Watson services that cannot be trained.
• Describe what Watson Knowledge Studio is.
• List the Watson services that can be trained with Watson Knowledge
Studio.
• Create a Watson service instance.
Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 2-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
2.1. IBM Watson overview

© Copyright IBM Corp. 2018, 2019 2-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson overview

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-2. IBM Watson overview

This section provides a high-level overview of IBM Watson

© Copyright IBM Corp. 2018, 2019 2-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Topics
• IBM Watson overview
• IBM Watson services on IBM Cloud
• Build with Watson

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-3. Topics

© Copyright IBM Corp. 2018, 2019 2-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson

• IBM Watson is the artificial intelligence (AI) offering from IBM.

• IBM Watson has the following capabilities:
ƒ Understands all forms of data.
ƒ Interacts naturally with people.
ƒ Learns and reasons at scale.
• You do not need to know the details of every associated AI subfield.
• You must have a high-level understanding of each subfield.
• You must know how to apply the correct AI technology to the
problem by using AI application programming interfaces (APIs) or a
ready-to-use AI framework.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-4. IBM Watson

IBM Watson is an AI system that enables a new partnership between people and computers. It is
the AI offering from IBM. Watson combines five core capabilities:
• Interacts with people more naturally based on the person’s preference.
• Quickly imports key industry materials by partnering with experts to scale and elevate expertise.
• Enables new products and services to sense, reason, and learn about users and the world
around them.
• Uses data to improve business processes and forecasting, which increases operational
effectiveness.
• Enhances exploration and discovery, which uncovers unique patterns, opportunities, and
actionable hypotheses.
IBM Watson includes AI technologies. Those technologies are complex, and to understand them
fully requires many years of study. However, to add AI capabilities to your applications, you do not
need to know the details that are associated with each AI subfield. You must have a high-level
understanding of each subfield, for example, natural language processing (NLP), computer vision,
and machine learning. Then, you must know how to apply the correct AI technology to a problem by
using AI APIs or a ready-to-use AI framework.

© Copyright IBM Corp. 2018, 2019 2-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson history

• Named after the first CEO of IBM, Thomas J. Watson.

• Originally designed as a QA system architecture named DeepQA.
• In 2011, the Watson computer system competed on Jeopardy! against
the two most successful champions: Brad Rutter and Ken Jennings.
Watson won the first place prize of $1 million.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-5. IBM Watson history

Watson was named after the first CEO of IBM, Mr Thomas J. Watson.
In 2011, the Watson computer system competed on Jeopardy! a US nationally televised quiz show,
against former winners Brad Rutter and Ken Jennings. Watson won the first place prize of $1
million. Watson had access to 200 million pages of structured and unstructured content that filled 4
TB of disk storage, including the full text of Wikipedia.
The original Watson system that won Jeopardy! was based on a QuestionAnswering (QA) system
architecture, which was developed for Watson to play the game and which is known as the
DeepQA architecture. This system was specifically developer to answer trivia question.
DeepQA was a software architecture for deep content analysis and evidence-based reasoning. It
uses advanced natural language processing (NLP), information retrieval, reasoning, and machine
learning. In summary, DeepQA generates and scores many hypotheses by using an extensible
collection of natural language processing, machine learning, and reasoning algorithms, which
gather and weigh evidence over both unstructured and structured content to determine the answer
with the best confidence. The answer with the strongest confidence is Watson’s final answer.
DeepQA was trained in the open domain Wikipedia which is very appropriate to answer trivia
questions.

© Copyright IBM Corp. 2018, 2019 2-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
The original DeepQA architecture, designed to play the Jeopardy! game, evolved trough several
iterations to the Watson services and offerings available today. And it will continue to evolve
through the years with the major advancements in AI.

© Copyright IBM Corp. 2018, 2019 2-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson relies on data, information, and expertise

Available as a set of open application programming interfaces (APIs),

software as a service (SaaS) tools and industry solutions.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-6. IBM Watson relies on data, information, and expertise

Data, information, and expertise create the foundation for working with Watson. The figure shows
examples of data and information that Watson can analyze and learn from, and derive new insights
that were never discovered before.

© Copyright IBM Corp. 2018, 2019 2-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson services offerings

• IBM Watson is available as the following offerings:
ƒ A set of services on IBM Cloud

ƒ Software as a Service (SaaS)

ƒ Set of industry solutions

ƒ Other solutions

• The focus of this unit is the IBM Watson services on IBM Cloud.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-7. IBM Watson services offerings

IBM Watson is available as a set of services on IBM Cloud, SaaS cloud offerings, and a set of
industry solutions. Besides the core offerings, a large set of resources and documentation are
available for application developers.
The focus of this unit (and this course) is on IBM Watson services on IBM Cloud only.

© Copyright IBM Corp. 2018, 2019 2-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
2.2. IBM Watson services on IBM Cloud

© Copyright IBM Corp. 2018, 2019 2-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson services on IBM

Cloud

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-8. IBM Watson services on IBM Cloud

This section provides an overview of the Watson services and tools available on IBM Cloud.

© Copyright IBM Corp. 2018, 2019 2-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Topics
• IBM Watson overview
• IBM Watson services on IBM Cloud
• Build with Watson

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-9. Topics

© Copyright IBM Corp. 2018, 2019 2-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson services on IBM Cloud - Summary

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-10. Watson services on IBM Cloud - Summary

The figure shows the Watson services on IBM Cloud circa 2018. These services will continue to be
enhanced and new services will be introduced in the future.
The following services are available as REST APIs and SaaS tools that developers can use to build
AI solutions or add AI features to their applications. See the website
https://www.ibm.com/watson/products-services/.
AI Assistant (Chatbot): Integrate diverse conversation technologies into your application:
• Watson Assistant: Quickly build a chat bot by using tools and dialog trees.
Data: Collect, organize and analyze your data, then achieve trust, scale, and automation across
your full AI lifecycle:
• Watson Studio: collaborative environment with AI tools that a team can use to collect and
prepare training data, and to design, train, and deploy machine learning models.
• Watson Machine Learning: Enables users to perform two fundamental operations of machine
learning: training and scoring.
• Watson Knowledge Catalog: Machine learning data catalog (MLDC) that enables you to access,
curate, categorize and share data, knowledge assets and their relationships, wherever they
reside.

© Copyright IBM Corp. 2018, 2019 2-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
Knowledge: Get insights through accelerated data optimization capabilities:
• Discovery: Unlock hidden value in data to find answers, monitor trends, and surface patterns.
• Discovery News: Explore news and blogs with smarter news from Watson that includes
concepts, sentiment, relationships and categories.
• Natural Language Understanding: NLP for advanced text analysis.
• Knowledge Studio: Teach Watson to discover meaningful insights in unstructured text.
Vision: Identify and tag content, and then analyze and extract detailed information that is found in
an image:
• Visual Recognition: Tag and classify visual content by using machine learning.
Speech: Converts text and speech with the ability to customize models:
• Speech to Text: Easily converts audio and voice into written text.
• Text to Speech: Converts written text into natural-sounding audio.
Language: Analyzes text and extracts metadata from unstructured content:
• Language Translator: Translates text from one language to another.
• Natural Language Classifier: Interprets and classifies natural language. Applies natural
language processing and machine learning techniques to return the best matching classes for a
sentence or phrase.
Empathy: Understands tone, personality, and emotional state:
• Personality Insights: Predicts personality characteristics through text.
• Tone Analyzer: Understands emotions and communication style in text.

© Copyright IBM Corp. 2018, 2019 2-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson Assistant (formerly Conversation)

• Adds a natural language interface to your application to automate
interactions with your users.
• Build the conversation flow and train the service by using an easy-to-
use web interface.
• Integrate Watson Assistant with other Watson services to enrich the
chatbot interaction experience.
• Example applications: Virtual agents and chat bots.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-11. Watson Assistant (formerly Conversation)

Watson Assistant
IBM Watson Assistant is a cognitive bot that you can customize for your business needs, and
deploy across multiple channels to bring help to your customers where and when they need it.
You can add a natural language interface to your application to automate interactions with your
users.
Example applications include virtual agents and chat bots that can integrate and communicate on
any channel or device, including mobile devices, messaging platforms, and robots.
Train the Watson Assistant service by using an easy-to-use web interface so that you can quickly
build natural conversation flows between your apps and users, and deploy scalable and
cost-effective solutions.

© Copyright IBM Corp. 2018, 2019 2-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson Discovery
• Adds cognitive search and content analytics to applications to identify
patterns, trends, and insights.
• Unlocks actionable insights into unstructured data.
• Unifies structured and unstructured data.
• Uses simple query language to eliminate the need for manual filtering of
results.
• Includes the Discovery API and Discovery tooling.
• Example application: Find answers to FAQs

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-12. Watson Discovery

Watson Discovery
Add a cognitive search and content analytics engine to applications to identify patterns, trends, and
actionable insights that drive better decision-making. Rapidly build cognitive, cloud-based
exploration applications that unlock actionable insights that are hidden in unstructured data.
Securely unify structured and unstructured data with pre-enriched content, and use a simplified
query language to eliminate the need for manual filtering of results.
With Discovery, you can prepare your unstructured data, create a query that will pinpoint the
information you need, and then integrate those insights into your new application or existing
solution.

© Copyright IBM Corp. 2018, 2019 2-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
The Discovery services includes:
• Discovery API: The Discovery service supports a number of SDKs to simplify the development
of applications. The SDKs are available for many popular programming languages and
platforms, including Node.js, Java, and Python.

© Copyright IBM Corp. 2018, 2019 2-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
• Discovery tooling: The Discovery service includes a complete set of online tools - the Discovery
tooling - to help you quickly setup an instance of the service and populate it with data. The
Discovery service tooling has been designed to save time by eliminating the need to use APIs
to configure and populate your service.
With Discovery you can build applications that extract the correct answers to FAQs by enriching
and searching data collections.

© Copyright IBM Corp. 2018, 2019 2-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Natural Language Understanding

• Analyze semantic features of text input, including the following items:
ƒ Concepts, Entities, Keywords, Categories, Sentiment, Emotion, Relations,
Semantic roles

• Categorize content.
• Develop custom annotation models to identify domain-specific entities
and relations in unstructured text by using Knowledge Studio.
• Example applications: Categorize news articles and blog posts and sort
them based on general concepts, keywords, and entities.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-13. Natural Language Understanding

Natural Language Understanding

Analyze text to extract metadata from content such as concepts, entities, keywords, categories,
sentiment, emotion, relations, semantic roles.
Categorize your content using a five-level classification hierarchy. View the complete list of
categories at
https://console.bluemix.net/docs/services/natural-language-understanding/categories.html#categor
ies-hierarchy.
Custom annotation models are developed by using Watson Knowledge Studio to identify industry-
and domain-specific entities and relations in unstructured text.
Example applications: Categorize news articles and blog posts and sort them based on general
concepts, keywords, and entities.

© Copyright IBM Corp. 2018, 2019 2-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Natural Language Classifier

• Applies AI techniques to return the best matching classes for a
sentence or phrase.
• You create a classifier instance by providing a set of representative
strings and a set of one or more correct classes for each training.
• After training, the new classifier can accept new questions or phrases
and return the top matches with a probability value for each match.
• Example applications:
ƒ Banking and finance: Classify investments, risks, and transactions.
ƒ Services: Categorize service queries, messages, and responses to help
address problems and deploy solutions quicker.
ƒ Email: Classify mail as spam or non-spam.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-14. Natural Language Classifier

Natural Language Classifier

The Natural Language Classifier service applies AI techniques to return the best matching classes
for a short text (sentence or phrase). For example, you submit a question and the service returns
keys to the best matching answers or next actions for your application.
You create a classifier instance by providing a set of representative strings and a set of one or more
correct classes for each training. After training, the new classifier can accept new questions or
phrases and return the top matches with a probability value for each match.
Example applications:
• Banking and finance: Classify investments, risks, and transactions.
• Services: Categorize service queries, messages, and responses to help address problems and
deploy solutions quicker.
• Email: Classify mail as spam or non-spam.

© Copyright IBM Corp. 2018, 2019 2-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Visual Recognition
• Uses deep learning algorithms to analyze images.
• Analyzes the images for scenes, objects, faces, colors, food, text,
explicit content, and other subjects that provide insights into the visual
content.
• A set of built-in models provides accurate results without training:
ƒ General model: Default classification from thousands of classes.
ƒ Face model: Facial analysis with age and gender.
ƒ Explicit model: Whether an image is inappropriate for general use.
ƒ Food model: Specifically for images of food items.
ƒ Text model (Private beta): Text extraction from natural scene images.

• Train custom models to create specialized classes.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-15. Visual Recognition

Visual Recognition
Visual Recognition understands the content of images. This service uses deep learning algorithms
to analyze images for scenes, objects, faces, colors, food, text, explicit content, and other subjects
that provide insights into the visual content. The response includes keywords that provide
information about the content.
A set of built-in models provides highly accurate results without training:
• General model: Default classification from thousands of classes.
• Face model: Facial analysis with age and gender.
• Explicit model: Whether an image is inappropriate for general use.
• Food model: Specifically for images of food items.
• Text model (Private beta): Text extraction from natural scene images

© Copyright IBM Corp. 2018, 2019 2-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
The Visual Recognition service can be used for diverse applications and industries, such as these:
• Manufacturing: Use images from a manufacturing setting to make sure products are being
positioned correctly on an assembly line.
• Visual Auditing: Look for visual compliance or deterioration in a fleet of trucks, planes, or
windmills in the field, train custom models to understand what defects look like.
• Insurance: Rapidly process claims by using images to classify claims into different categories.
• Social listening: Use images from your product line or your logo to track buzz about your
company on social media.
• Social commerce: Use an image of a plated dish to find out which restaurant serves it and find
reviews, use a travel photo to find vacation suggestions based on similar experiences, use a
house image to find similar homes that are for sale.
• Retail: Take a photo of a favorite outfit to find stores with those clothes in stock or on sale, use a
travel image to find retail suggestions in that area, use the photo of an item to find out its price in
different stores.
• Education: Create image-based applications to educate about taxonomies, use pictures to find
educational material on similar subjects.
• Public safety: Automated, real-time video stream analysis to include targeted observations such
as facial recognition and automated license-plate reading, identify a suspect’s car with unknown
whereabouts to locate instances of that model, parked or in motion, in any surveilled part of the
country.

© Copyright IBM Corp. 2018, 2019 2-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Speech to Text
• Converts human voice into the corresponding text.
• Uses machine intelligence to combine information about grammar and
language structure with knowledge of the composition of the audio
signal to generate an accurate transcription.
• Provides APIs that you can use to add speech transcription capabilities
to your applications.
• The languages that are currently available are English (US and UK),
Japanese, Arabic, Mandarin Chinese, Portuguese (Brazil), Spanish,
French, German, and Korean.
• Example applications:
ƒ Voice control of applications, embedded devices, and vehicle accessories
ƒ Transcribing meetings and conference calls
ƒ Dictating email messages and notes

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-16. Speech to Text

Speech to Text
The Speech to Text service converts the human voice into the corresponding text. Use this service
to convert audio and voice into text for quick understanding of content. It can be used anywhere
there is a need to bridge the gap between the spoken word and their written form, including voice
control of embedded systems, transcription of meetings and conference calls, and dictation of email
and notes. This easy-to-use service uses machine intelligence to combine information about
grammar and language structure with knowledge of the composition of the audio signal to generate
an accurate transcription.
The following languages are currently available: English (US), English (UK), Japanese, Arabic
(Modern Standard Arabic (MSA), Broadband model only), Mandarin Chinese, Portuguese (Brazil),
Spanish, French (Broadband model only), German (Broadband model only), and Korean.
The Speech to Text service can take an audio voice file as input and convert the audio into written
text.

© Copyright IBM Corp. 2018, 2019 2-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
This service can be used in practical applications such as these:
• Transcribe calls in a contact center to identify what is being discussed, when to escalate calls,
and to understand content from multiple speakers.
• Transcribe a technical explanation provided by a subject matter expert to help to create
documentation.
• Transcribe speech from a movie and create subtitles or captions.
• Transcribe voice mail messages to obtain a written log of messages left, for example, by clients
or patients.
• Create voice control applications, for example an automated home control system that is based
on your speech. Functions can include switching the light on and off, controlling electronic
devices, or even opening the front door remotely.

© Copyright IBM Corp. 2018, 2019 2-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Text to Speech
• Converts written text into natural sounding audio in various languages
and voices.
• The currently available languages are Portuguese (Brazil), English (UK
and US), French, German, Italian, Japanese, and Spanish.
• Example applications: Voice-driven and screenless applications, where
audio is the preferred method of output:
ƒ Interfaces for the disabled, such as assistance tools for the vision-impaired
ƒ Reading text and email messages aloud to drivers
ƒ Video-script narration and video voice over
ƒ Reading-based educational tools
ƒ Home-automation solutions

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-17. Text to Speech

Text to Speech
Use the Watson Text to Speech API to convert written text into natural sounding audio in various
languages and voices. The Text to Speech service processes text and natural language to generate
synthesized audio output with the appropriate cadence and intonation.
The service supports voices in the following languages: Brazilian Portuguese, English (UK and US
dialects), French, German, Italian, Japanese, and Spanish (Castilian, Latin American, and North
American dialects). The service offers at least one male or female voice, sometimes both, for each
language.
The service is appropriate for voice-driven and screenless applications, where audio is the
preferred method of output:
• Interfaces for the disabled, such as assistance tools for the vision-impaired
• Reading text and email messages aloud to drivers
• Video-script narration and video voice over
• Reading-based educational tools
• Home-automation solutions

© Copyright IBM Corp. 2018, 2019 2-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
This service can be used in practical applications such as these:
• Create audio narration from a written script for a variety of applications, such as online tutorials
for an e-learning course, audio books, and so on.
• Provide callers with information, such as company location, store hours, and account
information that is extracted from a database or organization’s documentation and converted to
audible speech.
• Develop interactive educational material for children.
• Communicate directions, hands-free.

© Copyright IBM Corp. 2018, 2019 2-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Language Translator
• Identifies the language of text and translates it into different languages
programmatically.
• High-quality, domain-specific text translation.
• The following domains and languages are supported:
ƒ The News domain to translate English to and from French, Spanish,
Portuguese, or Arabic.
ƒ The Conversational domain to translate English to and from Spanish or
Portuguese.
ƒ The Patent domain to translate Spanish, Portuguese, Japanese, or Korean
to English.

• Extend provided models to learn custom terms and phrases.

• Example application: Enable a help desk representative to assist
international customers through chat.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-18. Language Translator

Language Translator
This service provides high-quality and domain-specific text translation from one language to
another. It is one of the few offerings that focuses on domain-specific Statistical Machine
Translation.
The following domains and languages are supported:
• The News domain to translate English to and from French, Spanish, Portuguese, or Arabic.
• The Conversational domain to translate English to and from Spanish or Portuguese.
• The Patent domain to translate Spanish, Portuguese, Japanese, or Korean to English
You can create your own custom translation model. Most of the provided translation models in
Language Translator can be extended to learn custom terms and phrases or a general style that is
derived from your translation data.
Example application: Enable a help desk representative to assist international customers through
chat.

© Copyright IBM Corp. 2018, 2019 2-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Personality Insights
• Infers personality characteristics that can be extracted from text based
on three primary models:
ƒ Big Five personality characteristics: Agreeableness, Conscientiousness,
Extraversion, Emotional range, and Openness.
ƒ Needs describe which aspects of a product are likely to resonate with a
person: Excitement, Harmony, Curiosity, Ideal, Closeness, Self-
expression, Liberty, Love, Practicality, Stability, Challenge, and Structure.
ƒ Values describe motivating factors that influence a person's decision
making: Self-transcendence / Helping others, Conservation / Tradition,
Hedonism / Taking pleasure in life, Self-enhancement / Achieving success,
and Open to change / Excitement.

• Example applications:
ƒ Brand analytics and customer care
ƒ Market segmentation and campaigns

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-19. Personality Insights

Personality Insights
The Personality Insights service infers personality characteristics based on three primary models:
• Big Five personality characteristics represent the most widely used model for generally
describing how a person engages with the world. The model includes five primary dimensions:
Agreeableness, Conscientiousness, Extraversion, Emotional range, and Openness. Each
dimension has six facets that further characterize an individual according to the dimension.
• Needs describe which aspects of a product are likely to resonate with a person. The model
includes twelve characteristic needs: Excitement, Harmony, Curiosity, Ideal, Closeness,
Self-expression, Liberty, Love, Practicality, Stability, Challenge, and Structure.
• Values describe motivating factors that influence a person's decision making. The model
includes five values: Self-transcendence / Helping others, Conservation / Tradition, Hedonism /
Taking pleasure in life, Self-enhancement / Achieving success, and Open to change /
Excitement.

© Copyright IBM Corp. 2018, 2019 2-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
Watson Personality Insights derives insights from transactional and social media data to identify
psychological traits that determine purchase decisions, intent, and behavioral traits.
Use the Watson Personality Insights API in your applications to predict personality characteristics,
needs, and values that are extracted from written text.
• Enables deeper understanding of people's personality characteristics, needs, and values to
help engage users on their own terms.
• Extracts a set of personality and social traits based on the way a person communicates:
Agreeableness, openness, conscientiousness, introversion and extraversion, and emotional
range.
Examples applications:
• Brand analytics and customer care
• Market segmentation and campaigns

© Copyright IBM Corp. 2018, 2019 2-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Tone Analyzer
• Tone impacts the effectiveness of communication in different contexts.
• Watson Tone Analyzer uses linguistic analysis to identify various tones
at both the sentence and document level.
• It detects three types of tones from text:
ƒ Emotion (anger, disgust, fear, joy, and sadness)

ƒ Social tendencies (openness, conscientiousness, extroversion and

introversion, agreeableness, and emotional range)

ƒ Language styles (analytical, confident, and tentative)

• Example applications:
ƒ Understand how written communications are perceived and then improve the
tone of the communications.
ƒ Businesses can learn the tone of their customers' communications and then
respond appropriately to each customer.
Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-20. Tone Analyzer

Tone Analyzer
People show various tones, such as joy, sadness, anger, and agreeableness, in daily
communications. Such tones can impact the effectiveness of communication in different contexts.
Watson Tone Analyzer uses linguistic analysis to identify various tones at both the sentence and
document level. This insight can then be used to refine and improve communications.
It detects three types of tones:
• Emotion (anger, disgust, fear, joy, and sadness)
• Social propensities (openness, conscientiousness, extroversion and introversion,
agreeableness, and emotional range)
• Language styles (analytical, confident, and tentative) from text
Use the Watson Tone Analyzer API in your applications to understand emotions, social tendencies,
and perceived writing style.

© Copyright IBM Corp. 2018, 2019 2-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson Studio
• Collaborative environment with AI tools to collect and prepare training
data, and to design, train, and deploy machine learning models.
• It is a SaaS solution that is delivered on IBM Cloud.
• Watson Studio AI tools support popular frameworks, including:
TensorFlow, Caffe, PyTorch, and Keras.
• The architecture of Watson Studio is centered around the project.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-21. Watson Studio

Watson Studio
IBM Watson Studio is a collaborative environment with AI tools that a team can use to collect and
prepare training data, and to design, train, and deploy machine learning models.
It is a SaaS solution that is delivered on IBM Cloud.
Watson Studio provides a suite of tools for data scientists, application developers, and subject
matter experts (SMEs) to work collaboratively and easily with data. They can then use that data to
build, train, and deploy models at scale. These tools are preconfigured so that builders do not have
to spend time installing, setting up, and maintaining them. The built-in catalog function enables
knowledge sharing and retention. Watson Studio can infuse AI into your business.
It enables you to analyze data by using RStudio, Jupyter, and Python in a configured and
collaborative environment that includes added value, such as managed Spark and IBM Watson
Machine Learning.
The architecture of Watson Studio is centered around the project. A project is where you organize
your resources and work with data.

© Copyright IBM Corp. 2018, 2019 2-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
You can think of Watson Studio AI tools in four categories:
• Visual recognition
• Natural language classification
• Machine learning
• Deep learning
For more information see
https://dataplatform.cloud.ibm.com/docs/content/getting-started/overview-ws.html?context=analytic
s

© Copyright IBM Corp. 2018, 2019 2-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson Machine Learning

• Machine Learning is a service on IBM Cloud with features for training

and deploying machine learning models and neural networks. It
provides:
ƒ Interfaces for building, training, and deploying models: Python client library
external link, Command line interface, REST API external link.
ƒ Deployment infrastructure for hosting your trained models.
ƒ Hyperparameter optimization for training complex neural networks.
ƒ Distributed deep learning for distributing training runs across multiple
servers.
ƒ GPUs for faster training.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-22. Watson Machine Learning

Watson Machine Learning

IBM Watson Machine Learning is a full-service IBM Cloud offering that makes it easy for data
scientists and developers to work together to integrate predictive analytics with their applications.
The Watson Machine Learning service enables your organization to use the models in your
end-to-end solutions without the impact of licensing, installation, and configuration that is required
by the same products when they are installed on-premises. You can use machine learning and
deep learning models in production. Use an automated and collaborative workflow to grow
intelligent business applications easily and with more confidence.
Using Watson Machine Learning, you can build sophisticated analytical models, trained with your
own data, that you can deploy for use in applications.

© Copyright IBM Corp. 2018, 2019 2-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
Machine Learning is a service on IBM Cloud with features for training and deploying machine
learning models and neural networks:
• Interfaces for building, training, and deploying models: Python client library external link,
Command line interface, REST API external link
• Deployment infrastructure for hosting your trained models
After you create, train, and evaluate a model, you can deploy it. When you deploy a model you
save it to the model repository that is associated with your Watson Machine Learning service.
Then, you can use your deployed model to score data and build an application.
• Hyperparameter optimization for training complex neural networks
You can run your experiments with HPO to easily find the best quality model. Hyperparameter
Optimization (HPO) is a mechanism for automatically exploring a search space of potential
Hyperparameters, building a series of models and comparing the models using metrics of
interest. To use HPO you must specify ranges of values to explore for each Hyperparameter.
• Distributed deep learning for distributing training runs across multiple servers
Deep learning models training can be significantly accelerated with distributed computing on
GPUs.
• GPUs for faster training
IBM Watson Machine Learning deep learning simplifies the process to train models in parallel
with an on-demand graphics processing units (GPU) compute cluster that you can scale to your
specific needs.
For an overview of Watson Machine Learning, see: https://youtu.be/5kMDIBpxi_k

© Copyright IBM Corp. 2018, 2019 2-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

IBM Watson Knowledge Studio

• Enables developers and domain experts to collaborate and create a
machine learning model that understands the linguistic nuances,
meaning, and relationships specific to an industry or domain.

• Provides easy-to-use tools for annotating unstructured domain

literature.
• The annotations are used to create a custom machine learning
model that understands the language of the domain.
• The model can be deployed directly to IBM Watson Explorer, Watson
Natural Language Understanding, and Watson Discovery.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-23. IBM Watson Knowledge Studio

IBM Watson Knowledge Studio

IBM Watson Knowledge Studio enables developers and domain experts to collaborate and create a
machine learning model that understands the linguistic nuances, meaning, and relationships
specific to an industry or domain.
Provides easy-to-use tools for annotating unstructured domain literature, and uses those
annotations to create a custom machine-learning model that understands the language of the
domain.
These annotators can identify mentions and relationships in unstructured data and be easily
administered throughout their lifecycle by using one common tool.
Annotator components can be deployed directly to IBM Watson Explorer, Watson Natural Language
Understanding, and Watson Discovery.

© Copyright IBM Corp. 2018, 2019 2-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
The diagram illustrates how it works:
1. Based on a set of domain-specific source documents, the team creates a type system that
defines entity types and relation types for the information of interest to the application that will
use the model.
2. A group of two or more human annotators annotates a small set of source documents to label
words that represent entity types, to identify relation types where the text identifies relationships
between entity mentions, and to define coreferences, which identify different mentions that refer
to the same thing, that is, the same entity. Any inconsistencies in annotation are resolved, and
one set of optimally annotated documents is built, which forms the ground truth.
3. Watson Knowledge Studio uses the ground truth to train a model.

© Copyright IBM Corp. 2018, 2019 2-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
2.3. Build with Watson

© Copyright IBM Corp. 2018, 2019 2-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Build with Watson

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-24. Build with Watson

This section provides the initial steps to get started using the Watson APIs. It also lists the key
resources available to developers.

© Copyright IBM Corp. 2018, 2019 2-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Topics
• IBM Watson overview
• IBM Watson services on IBM Cloud
• Build with Watson

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-25. Topics

© Copyright IBM Corp. 2018, 2019 2-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Building AI solutions with IBM Watson services on IBM Cloud

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-26. Building AI solutions with IBM Watson services on IBM Cloud

Watson services on IBM Cloud provide a cloud-hosted marketplace where application providers of
all sizes and industries can tap into resources for developing applications that are powered by
Watson services. Developers can combine the Watson services (and other services that are
available in IBM Cloud) with additional logic to build applications with AI capabilities.
The goal of Watson services on the IBM Cloud is to provide flexible platform for building AI
applications in industry domains. The microservices architecture enables developers to envision a
broad range of potential applications by mixing and matching services.
The available resources include developer toolkits, educational materials, and access to Watson
APIs and SaaS tools. This approach makes IBM Watson technology available as a development
platform in the cloud to enable a worldwide community of software application providers to build a
new generation of applications that is infused with Watson AI capabilities.

© Copyright IBM Corp. 2018, 2019 2-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson services and domain adaptation

• AI systems must be trained to understand new domains and perform
new tasks.
• Built-in models included in Watson services are generic or geard
towards popular applications of the service.
ƒ The goal is to enable the initial use of the service with no training but the
accuracy for a particular application might not be satisfactory.

• Services must be trained to improve their performance for specific

application.
• Some Watson services cannot be trained by users.
ƒ IBM is in charge of training these services.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-27. Watson services and domain adaptation

One key element of AI systems is the capability to learn and adapt overtime. Rather than being
explicitly programmed, AI systems learn from their interactions with their users and from their
experiences with their environment. Machine learning gives computers the ability to learn and act
without being explicitly programmed. This means that the model gets better over time by learning
from its mistakes and new experiences (being exposed to new data). When developing machine
learning models, the models are built from a fixed source, for example, open domain Wikipedia,
and they are deployed to similar or different domains, for example the Travel domain. To improve
accuracy, the new domain data must be used to train the model. This task is known as domain
adaptation.
Like humans, AI systems must be trained to understand new domains and perform new tasks. For
example, understanding medical records to identify medical conditions and associated
prescriptions requires deep knowledge of drugs and diseases. In order to be able to perform these
tasks, humans go to college, get a medical degree and, after many years of training and study,
become doctors. Likewise, AI systems must be trained to
become experts in specific domains. Training is performed by subject matter experts (SMEs)
providing human supervision and domain-specific knowledge bases representing entities and
relations of interest for the new domain. A similar process must be followed to apply Watson
technology to specific domains.

© Copyright IBM Corp. 2018, 2019 2-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
Domain adaptation consists of the necessary activities to adapt an open-domain system to a
specific domain (a closed-domain).
Information extraction analytics that are provided by Watson APIs are open domain, which means
that they can recognize named entities that belong to basic types, such as company, person, and
location, but they cannot recognize more specific distinctions, such as names of banks, insurance
companies, and their products. Likewise, the built-in models in the Visual Recognition service can
classify thousands of classes for popular images, faces, food but the models must be trained to
improve performance for a specific images classification.
To become an SME in a specific industry or domain, some Watson services must be trained.

© Copyright IBM Corp. 2018, 2019 2-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson services and domain adaptation (cont.)

• Services that can be trained by the user.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-28. Watson services and domain adaptation (cont.)

This figure shows the Watson services that you can train to adapt them to a closed domain:
• Watson Assistant: This service must be trained to recognize what the user is saying and
respond accordingly.
• Discovery: The relevance of natural language query results can be improved in the Discovery
service with training. Relevancy training teaches the service what results should be surfaced
higher than others so that your users can get the correct answer to their question faster. You
also can use IBM Watson Knowledge Studio to train a custom model and deploy it to the
Discovery service.
• Language Translator service: This service can be trained over time to provide better accuracy
when running translations. To train, the service must learn from previous translations. For
example, Language Translator can be trained to reduce the error in translating financial news
across languages. Another example is that you are creating a translator for customer support
and you have company-specific terms that you want handled in a certain way in conversations.
A third example is that you are creating a way for your engineers in one country to look up
patent data in another language, and you often file patents on a specific technology. You can
use your own data to create a custom dictionary and a custom translation model in the
Language Translator service.

© Copyright IBM Corp. 2018, 2019 2-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty
• Natural Language Classifier: This service can be trained to identify new classes in unstructured
text, such as financial news from blog posts.
• Natural Language Understanding: This service is trained on an open domain by default. With
custom annotation models that are developed by using IBM Watson Knowledge Studio, you can
further customize the service to identify domain-specific entities and relations in your content.
• Speech to Text: This service can be customized for a particular domain by creating a language
model to provide the nuances in that domain in terms of vocabularies and word pronunciations.
By training the service, you can improve the accuracy of speech recognition for domains such
as medicine, law, information technology, and others.
• Text to Speech: This service provides a customization interface so that you can create a
dictionary of words and their translations for a specific language. This dictionary of words and
their translations is referred to as a custom voice model.
• Visual Recognition: This service includes a set of built-in classes that provides highly accurate
results without training. You can also train and create a custom models (or custom classifiers).
With a custom model, you can train the Visual Recognition service to classify images to suit
your business needs. By creating a custom model, you can use the Visual Recognition service
to recognize images that are not available with pre-trained classification, for example, to
recognize company logos in pictures.
• Knowledge Studio: This service is used to train Watson with the language of your domain by
using custom machine learning models that identify entities and relationships that are unique to
your industry in unstructured text.

© Copyright IBM Corp. 2018, 2019 2-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson services and domain adaptation (cont.)

• Services that cannot be trained by the user.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-29. Watson services and domain adaptation (cont.)

The figure illustrates the Watson services that cannot be trained by the user. For these services,
IBM is in charge of the required training.

© Copyright IBM Corp. 2018, 2019 2-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Getting started with Watson services on IBM Cloud

You must complete these steps to use the Watson services on IBM
Cloud:
1. Set up your IBM Cloud account.
2. Find and select the Watson service in the IBM Cloud catalog.
3. Create the service instance.
4. Get the service credentials to authenticate to your service from your
application.
5. Start coding your application and calling the Watson APIs to infuse AI
capabilities into your app.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-30. Getting started with Watson services on IBM Cloud

To get started with Watson services on IBM Cloud, you must complete these steps before you can
use the service in your applications:
1. Set up your IBM Cloud account.
2. Find and select the Watson service that you need from the IBM Cloud catalog.
3. Create a service instance. IBM Cloud provides resources to your applications through a service
instance.
4. Get service credentials. You need the service credentials to authenticate to your service
instance from your application.
5. Start coding your application and calling the Watson APIs to infuse AI capabilities into your app.
For more information about these steps, see Exercise 1.

© Copyright IBM Corp. 2018, 2019 2-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Watson SDKs
• Enable developers to use Watson REST APIs in their favorite
programming language.
• Developers should consider using the SDKs instead of calling the REST
APIs directly.
• Watson SDKs supported by IBM:
ƒ Android SDK, Java SDK, Node.js SDK, Python SDK, Ruby SDK, Salesforce
SDK, Swift SDK, .NET SDK, OpenWhisk SDK, and Unity SDK

• Watson SDKs from the Watson community of developers:

ƒ Go SDK, PHP SDK, Ruby wrappers, Scala SDK

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-31. Watson SDKs

© Copyright IBM Corp. 2018, 2019 2-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Additional resources for developers

For more information access these resources:

• Explore the complete list of Watson APIs: Watson Products

and Services
• Get started on IBM Cloud : IBM Cloud essentials
• Access developer’s resources:
ƒ Build with Watson
ƒ Documentation and API Reference
ƒ Watson SDKs
ƒ Building Cognitive Applications with IBM Watson Services
ƒ AI articles and tutorials
ƒ Watson webinars
ƒ Building with Watson: Application Starter Kits for developers
ƒ Watson Starter Kits

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-32. Additional resources for developers

• Watson products and services: https://www.ibm.com/watson/products-services/

• IBM Cloud essentials: https://developer.ibm.com/courses/all/bluemix-essentials/
• Build with Watson: https://console.bluemix.net/developer/watson/dashboard
• Documentation and API Reference:
https://console.bluemix.net/developer/watson/documentation
• Watson SDKs:
https://console.bluemix.net/docs/services/watson/getting-started-sdks.html#sdks
• Building Cognitive Applications with IBM Watson Services:
http://www.redbooks.ibm.com/redbooks.nsf/pages/cognitiveapps?Open
• AI articles and tutorials: https://developer.ibm.com/technologies/artificial-intelligence/
• Watson webinars: https://www.ibm.com/watson/webinars/
• Building with Watson: Application Starter Kits for developers:
https://developer.ibm.com/tv/building-with-watson-application-starter-kits-for-developers/
• Watson Starter Kits: https://cloud.ibm.com/developer/watson/starter-kits

© Copyright IBM Corp. 2018, 2019 2-49

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Unit summary
• Explain what IBM Watson is.
• List the Watson service.
• Explain the capabilities of each Watson service.
• Describe the purpose of training the various Watson services to adapt
them to a closed-domain.
• List the Watson services that can be trained.
• List the Watson services that cannot be trained.
• Describe what Watson Knowledge Studio is.
• List the Watson services that can be trained with Watson Knowledge
Studio.
• Create a Watson service instance.
Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-33. Unit summary

© Copyright IBM Corp. 2018, 2019 2-50

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review questions
1. Enables applications to use natural language to
automatically respond to user questions:
A. Natural Language Understanding
B. Watson Assistant
C. Natural Language Classifier
D. Discovery
E. Speech to Text.

2. Provides tools that SMEs can use to annotate unstructured

domain literature, and uses those annotations to create a
custom machine-learning model that understands the
language of the domain. :
A. Watson Studio
B. Watson Machine Learning
C. Watson Knowledge Studio
D. Watson Health

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-34. Review questions

© Copyright IBM Corp. 2018, 2019 2-51

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review questions (cont.)

3. True or False: The Personality Insights service analyzes text
to extract metadata from content, such as concepts, entities,
keywords, categories, sentiment, emotion, relations, and
semantic roles.

4. The following Watson services cannot be trained by users:

A. Watson Assistant.
B. Personality Insights.
C. Visual Recognition.
D. Tone Analyzer.
E. A and D.
F. B and D.
G. C and D.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-35. Review questions (cont.)

© Copyright IBM Corp. 2018, 2019 2-52

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review questions (cont.)

5. This Watson service requires Watson Knowledge Studio to
be customized for a specific domain:
A. Visual Recognition.
B. Natural Language Understanding.
C. Watson Assistant.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-36. Review questions (cont.)

© Copyright IBM Corp. 2018, 2019 2-53

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review answers
1. Enables applications to use natural language to automatically
respond to user questions:
A. Natural Language Understanding
B. Watson Assistant
C. Natural Language Classifier
D. Discovery
E. Speech to Text
2. Provides tools that SMEs can use to annotate unstructured
domain literature, and uses those annotations to create a
custom machine-learning model that understands the
language of the domain. :
A. Watson Studio
B. Watson Machine Learning
C. Watson Knowledge Studio
D. Watson Health

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-37. Review answers

© Copyright IBM Corp. 2018, 2019 2-54

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review answers (cont.)

3. True or False: The Personality Insights service
analyzes text to extract metadata from content, such
as concepts, entities, keywords, categories,
sentiment, emotion, relations, and semantic roles.
The answer is: False
The Natural Language Understanding service
performs this task.

4. The following Watson services cannot be trained by users:

A. Watson Assistant.
B. Personality Insights.
C. Visual Recognition.
D. Tone Analyzer.
E. A and D.
F. B and D.
G. C and D

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-38. Review answers (cont.)

© Copyright IBM Corp. 2018, 2019 2-55

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Review answers (cont.)

5. This Watson service requires Watson Knowledge Studio to
be customized for a specific domain:
A. Visual Recognition.
B. Natural Language Understanding.
C. Watson Assistant.

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-39. Review answers (cont.)

© Copyright IBM Corp. 2018, 2019 2-56

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Exercise: Exploring Watson

services

Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-40. Exercise: Exploring Watson services

© Copyright IBM Corp. 2018, 2019 2-57

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 2. Introduction to IBM Watson

Uempty

Exercise objectives
• This exercise introduces you to Watson REST APIs. You will
use cURL to submit requests to and receive responses from
the following Watson services:
ƒ Natural Language Understanding
ƒ Visual Recognition
ƒ Tone Analyzer
ƒ Language Translator

• After completing this exercise you should be able to:

ƒ Create Watson service instances.
ƒ Copy credentials from a service instance.
ƒ Submit API calls with the appropriate parameters.
ƒ Analyze the response that is returned from the Watson service.
ƒ Use Watson API reference documentation.
Introduction to IBM Watson © Copyright IBM Corporation 2019

Figure 2-41. Exercise objectives

After completing this exercise, you should be able to accomplish the following tasks:
• Create Watson service instances.
• Copy credentials from a service instance.
• Submit API calls with the appropriate parameters.
• Analyze the response that is returned from the Watson service.
• Use Watson API reference documentation.

© Copyright IBM Corp. 2018, 2019 2-58

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Unit 3. Introduction to IBM Watson

Studio
Estimated time
00:30

Overview
This unit provides a high level overview of IBM Watson Studio, its components, key applications
and the value added by the IBM offering.

© Copyright IBM Corp. 2018, 2019 3-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Unit objectives
• Describe Watson Studio.
• Identify industry use cases.
• List Watson Studio offerings.
• Create Watson Studio projects.
• Describe Watson Studio and Spark.
• Describe Watson Studio and Object Storage.
• Explain Watson Studio high availability considerations.
• Prepare and analyze data.
• Use Jupyter notebooks.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 3-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
3.1. Watson Studio overview

© Copyright IBM Corp. 2018, 2019 3-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio overview

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-2. Watson Studio overview

© Copyright IBM Corp. 2018, 2019 3-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Topics
• Watson Studio overview
• Watson Studio components
• Jupyter notebook

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-3. Topics

© Copyright IBM Corp. 2018, 2019 3-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

What is Watson Studio

Watson Studio is a collaborative platform for data scientists, built on
open source components and IBM added value, and is available in the
cloud and on-premises.
ƒ Collaborative platform:
í Community environment for sharing resources, tutorials, and data sets
í Simplified communication between different users and job roles
ƒ Open-source components: Python, Scala, R, SQL, Apache Spark,
and notebooks (Jupyter and Zeppelin)
ƒ IBM added value: Watson Machine Learning, Flow editor, Decision
Optimization, SPSS predictive analytics algorithms, analytics
dashboard, and more
ƒ Watson Studio Cloud, Watson Studio Local, and Watson Studio
Desktop

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-4. What is Watson Studio

Watson Studio is a collaborative platform for data scientists that is built on open source
components and IBM added value, and is available in the cloud or on-premises. The
collaborative platform enables the users, whether they are data scientists, data engineers, or
application developers to share resources and work together seamlessly within the platform.
Watson Studio is built upon open source components such as Python, Scala, R, SQL, Apache
Spark, and notebooks.
If the open source tools are not enough for your needs, IBM added value components such as
Watson Machine Learning, Flow editor, Decision Optimization, SPSS predictive analytics
algorithms, analytics dashboard, and more.
Watson Studio is available as three different offerings:
• Watson Studio Cloud, which is what you use in this course.
• Watson Studio Local, which is the on-premises version.
• Watson Studio Desktop is a light-weight version that you can install on your notebook.
This course uses Watson Studio Cloud.

© Copyright IBM Corp. 2018, 2019 3-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
For more information, see:
• Watson Studio Overview
https://dataplatform.cloud.ibm.com/docs/content/getting-started/overview-ws.html
• Decision Optimization https://dataplatform.cloud.ibm.com/docs/content/DO/DOinWStudio.html
• SPSS predictive analytics algorithms
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/spss-algorithms.html?audience=
wdp
• Analytics dashboard
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/analytics-dashboard.html?audie
nce=wdp

© Copyright IBM Corp. 2018, 2019 3-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Correct tool for the correct job

Data Engineer
OUTPUT INPUT Designs how data is organized
and ensures operability.
Deliver and Understand
Deploy Model. Problem and
Domain.
Data Scientist
Communicate Import Goes deep into the data to draw
Results. Data. hidden insights for the business.
Watson Studio

Create Explore and Business Analyst

and Build Understand Works with data to apply insights
Model. Data. to the business strategy.
Cognos Analytics

Transform:
Evaluate App Developer
Transform: Clean.
. Plugs into data and models and
Shape. writes code to build apps.
IBM Cloud
ANALYSIS
Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-5. Correct tool for the correct job

Open-source tools give you a wide range of choices. The downside of having too many choices is
knowing the correct one to pick. Essentially, you want to pick the correct tool for the correct job.
Watson Studio is no exception.
Watson Studio is designed for a specific persona, but other personas can use it as it relates to their
jobs.
Look at the diagram on the slide. Starting from the top and going clockwise, you have the input,
analysis, and output phases. Within each phase are the objectives of that phase. Each objective
can overlap between various user personas.
Look at the list of personas on the right side: the data engineer, the data scientist, the business
analyst, and the app developer. Each persona has primary tools that helps them do their job. For
example, the data scientist's main tool is Watson Studio.
Also, there might be a team of different personas. Whatever the case is, you must decide what tool
is correct for the job, regardless of the personas. The definitions of personas can vary between
different companies and evolve over time.

© Copyright IBM Corp. 2018, 2019 3-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
In addition to the tailored interface of Watson Studio, collaboration ties the team and the
organization together by enabling them to share projects, code, and ideas. Imagine a data engineer
builds a new data source and shares that asset with the data scientist and the business analyst.
The business analyst immediately builds the reports and dashboards they need. The data scientist
experiments with the data and builds a model that passes all the tests and can be used with new
applications. The team can immediately share that model with the application developer, who
deploys a new application by using the model. As this project progresses, the team members
update and share their statuses with the team, asking questions and sharing ideas or requirements.
In this scenario, data and analytics development become a team effort and is no longer done in
silos. Additionally, because these assets can be published, other departments can reuse these
assets, making the entire organization more agile.

© Copyright IBM Corp. 2018, 2019 3-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Industry use cases

Retail Transportation
Shopping experience End-to-end customer experience
Loss & fraud prevention Operations planning & optimization
Task & workforce optimization Predictive maintenance
Pricing & assortment optimization Route and asset optimization
Banking Media and Entertainment
Optimize offers & cross-Sell Audience & fan insight
Risk management Social media insight
Fraud and crime management Content demand forecasting
Financial performance Marketing & advertising optimization
Manufacturing Telco
Inventory optimization Subscriber analytics
Predictive maintenance IOT analytics
Health, safety, & environment Proactive marketing
Production planning and scheduling Network design

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-6. Industry use cases

Data science spans multiple industries, but you can see that data analysis applied to some of these
use cases is not entirely new. In fact, organizations have been doing these types of activities for
many years. The advantage that you have with Watson Studio is that you can easily collaborate
with other data scientists by using well-known tools that are widely used in the industry.

© Copyright IBM Corp. 2018, 2019 3-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

IBM Watson Studio

Learn Create Collaborate

Built-in learning to get The best of open source Community and social
started or go the and IBM added vale to features that provide
distance with advanced create state-of-the-art meaningful
tutorials. data products. collaboration.

http://datascience.ibm.com

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-7. IBM Watson Studio

Watson Studio is built as a collaborative platform. Watson Studio provides an easy way for you to
learn how to start using the platform. You can create state-of-the-art products that are based on the
data that you derive by using open source and IBM added value tools. As you innovate, you can
collaborate with your team and the community to share and gain insights.

© Copyright IBM Corp. 2018, 2019 3-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio offerings

• Watson Studio Cloud (public cloud):
ƒ IBM Cloud subscription (https://datascience.ibm.com).
ƒ https://github.com/IBMDataScience.
• Watson Studio Local (private cloud and on-premises):
ƒ Run on your own clusters.
ƒ Same tools and features.
• Watson Studio Desktop (local workstation):
ƒ Download and try on your desktop.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-8. Watson Studio offerings

Watson Studio is available in the following offerings:

• Watson Studio Cloud is available through IBM Cloud as the public cloud option. To use it, you
must have an IBM Cloud account. If you do not already have one, you will be directed to
register with IBM Cloud the first time you attempt to access the Watson Studio environment.
• IBM Watson Studio Local is a ready-to-use enterprise solution for data scientists and data
engineers. It offers a suite of data science tools, such as RStudio, Spark, Jupyter, and Zeppelin
notebooks, that are integrated with proprietary IBM technologies. This offering can be installed
on a private cloud or on-premises on the organization’s servers. It includes the same tools and
features that are available in Watson Studio Cloud.
• Watson Studio Desktop is the local version of the tool that you install on your local machine. It
enables you to experience the Watson Studio tooling before you decide on one of the other two
options.

© Copyright IBM Corp. 2018, 2019 3-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
For more information, see the following resources:
Watson Studio Cloud:
https://dataplatform.cloud.ibm.com/docs/content/getting-started/overview-ws.html
Watson Studio Local:
https://content-dsxlocal.mybluemix.net/docs/content/SSAS34_current/local/overview.html
Watson Studio Desktop:
https://www.ibm.com/support/knowledgecenter/SSBFT6_1.1.0/wsd/overview.html

© Copyright IBM Corp. 2018, 2019 3-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio and other IBM Cloud services

• Watson Studio is a part of Watson Data Platform:
ƒ All Watson Data Platform services are seamlessly integrated and loosely
coupled through IBM Cloud.
• Examples:
ƒ Watson Studio is aware of the Watson Machine Learning deployment
service.
ƒ Watson Studio is aware of Db2 Warehouse on Cloud (formerly dashDB),
Analytics Engine, and other data sources.
ƒ Watson Studio is aware of created Apache Spark services.
• The services do not depend on each other and some can be used as
stand-alone (loosely coupled).

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-9. Watson Studio and other IBM Cloud services

Watson Studio is part of the Watson Data Platform and integrates seamlessly, but coupled loosely,
with other tools through IBM Cloud. Here are some examples about how Watson Studio can work
with other tools:
• Watson Studio is aware of the Watson Machine Learning deployment service.
• Watson Studio is aware of Db2 Warehouse on Cloud (formerly dashDB), IBM Analytics Engine,
and other data sources.
• Watson Studio is aware of created Apache Spark services.
Each service is independent of the other ones, so you use only what you need.

© Copyright IBM Corp. 2018, 2019 3-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio high availability (public cloud)

• Designed for 24x7 availability: Continuous availability and continuous
delivery
• Backup and recovery:
ƒ Watson Studio is disaster-resistant.
ƒ Notebooks in Watson Studio are stored in a three-way Cloudant cluster in
multiple geographic zones.
ƒ Watson Studio provides integration with GitHub and an interface for
downloading notebooks if the customer wants to use their own backup.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-10. Watson Studio high availability (public cloud)

Watson Studio is designed for 24x7 availability, that is, continuous delivery and availability.
Features and updates are rolled out without downtime. Notebooks in Watson Studio are stored in a
three-way Cloudant cluster in multiple geographic zones. Watson Studio also provides integration
with GitHub so that you can manually download the notebooks if you want to use your own
backups.

© Copyright IBM Corp. 2018, 2019 3-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
3.2. Watson Studio components

© Copyright IBM Corp. 2018, 2019 3-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio components

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-11. Watson Studio components

© Copyright IBM Corp. 2018, 2019 3-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Topics
• Watson Studio overview
• Watson Studio components
• Jupyter notebook

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-12. Topics

© Copyright IBM Corp. 2018, 2019 3-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Projects
• The architecture of Watson Studio is centered around the project.
• Projects are a way to organize resources for a specific data science
task or goal.
• Integrate collaborators, data and analytic assets, tools, community
resources, your own data and so on, to support finding insights for a
well defined or narrow goal.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-13. Projects

The architecture of Watson Studio is centered on projects where everything is seamlessly

integrated. You create and organize projects to suit your business needs. Projects consist of data
assets, collaborators, analytic assets, and community resources that are combined with many open
source and added value tools.
Data assets are the files in your object store or connections, such as a database, data services,
streaming data, and other external files.
Collaborators can be assigned to your projects as admins, editors, or viewers.
Analytic assets are the notebooks and the models that you develop.
Watson Studio has a suite of tools that is available to help you with your job in the open source
space. It also has a suite of added value tools such as Decision Optimization Watson Machine
Learning, and Streaming Analytics.

© Copyright IBM Corp. 2018, 2019 3-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
You can think of Watson Studio AI tools in four categories:
• Visual recognition
• Natural language classification
• Machine learning
• Deep learning
The runtime environment of Watson Studio is Apache Spark.
For more information, see
https://dataplatform.cloud.ibm.com/docs/content/getting-started/overview-ws.html?context=analytic
s.

© Copyright IBM Corp. 2018, 2019 3-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Creating a project
When you create a project in Watson Studio, you choose from these
project starters.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-14. Creating a project

When you create a project in Watson Studio, you choose from these project starters:
Standard: Add collaborators and data assets. Add services as you need them.
Business Analytics: Visualize and share data in dashboards without coding.
Data Engineering: Cleanse and shape data with a Data Refinery flow.
Data Science: Analyze data with Jupyter notebooks or RStudio.
Deep Learning: Develop neural networks and test them in deep learning experiments.
Modeler: Build, train, test, and deploy machine learning models.
Streams Flow: Ingest streaming data with a streams flow.
Visual Recognition: Analyze and classify images in models.
All project starters include data assets and the IBM Cloud Object Storage service to store project
files. After you create a project, you can add other analytical assets and associate other services.

© Copyright IBM Corp. 2018, 2019 3-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio and Cloud Object Storage

• Projects require an object storage to store non-database data sources.
• An IBM Cloud Object Storage instance can be created when the
project is created.
ƒ A project can be associated with an existing Cloud Object Storage instance.
• Information stored in IBM Cloud Object Storage is encrypted and
resilient.
• Each project has its own dedicated bucket.
ƒ Buckets can be managed from the Watson Studio project interface.
• Cloud Object Storage supports two APIs:
ƒ Swift API: Available through Watson Studio
ƒ Amazon Simple Storage Service (S3) API

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-15. Watson Studio and Cloud Object Storage

Object storage provides the space where unstructured data for your project is stored.
An IBM Cloud Object Storage instance can be created at project creation time or a new project can
be associated with an existing Cloud Object Storage instance.
Object Storage supports two APIs:
• The Swift API, which is available through Watson Studio.
• The S3 API, where you provide external credentials.
Information stored with IBM Cloud Object Storage is encrypted and resilient.
Cloud Object Storage uses buckets to organize the data. Each project has its own dedicated
bucket.
The Cloud Object Storage can be managed from the Watson Studio project interface.

© Copyright IBM Corp. 2018, 2019 3-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Creating a project and defining its storage

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-16. Creating a project and defining its storage

Projects include integration with IBM Cloud Object Storage for storing project assets. When a new
project is created, a new Cloud Object Storage service is created to provide an unstructured cloud
data store. It is also possible to associate a project with an existing Cloud Object Storage.
To create a new project:
1. Click + New.
2. Enter a name for the project.
3. In the Define storage pane, click Add.
4. Click Refresh.
5. The Cloud Object Storage service page with the New tab selected is displayed. Click Create.
6. Click Refresh in the project page.
7. The newly created Cloud Object Storage instance is associated with the project.
8. Click Create to create the project.

© Copyright IBM Corp. 2018, 2019 3-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio project tabs

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-17. Watson Studio project tabs

The Watson Studio project page includes tabs with specific information about the project. The
following tabs are included:
Overview. Provides basic information about the project such as:
• Description
• Storage usage
• Collaborators
• Bookmarks
• Recent activity
Assets. Lists all the different types of assets that you can add to you project such as:
• Data assets
• Models
• Notebooks
• Dashboards

© Copyright IBM Corp. 2018, 2019 3-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
• Experiments
• Modeler flows
The project starter you choose affects the type of analytic assets you see on the Assets page in the
project. All project starters include data assets and the IBM Cloud Object Storage service to store
project files. After you create a project, you can add other analytical assets and associate other
services.
Environments. In this tab you can define the hardware size and software configuration for the
runtime associated with Watson Studio tools. An environment definition defines the hardware and
software configuration that you can use to run tools like notebooks, model builder, or the flow editor
in Watson Studio. With environments, you have dedicated resources and flexible options for the
compute resources used by the tools.
Bookmarks. Lists the community content that you have bookmarked; you can easily access that
content from this project.
Deployments. Contains any models that you created and deployed, for example machine learning
models.
Access Control. Here you can add an manage additional collaborators for your project.
Settings. Project settings is the area to define key aspects of your project like its name and
description. Use Settings to add tools and key services, check storage, and define access tokens.
For more information, see
https://dataplatform.cloud.ibm.com/docs/content/manage-data/project-tools.html?context=analytics
.

© Copyright IBM Corp. 2018, 2019 3-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Assets
• An asset is an artifact in a project that contains information, or
metadata, about data or data analysis.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-18. Assets

An asset is an artifact in a project that contains information, or metadata, about data or data
analysis.
Data assets are the types of assets that point to data, for example, a file or a data set that is
accessed through a connection to an external data source.
Analytical assets are the types of assets that run code to analyze data.
An asset might have associated files or require specific IBM Cloud services. For example, many
types of analytical assets require a service.
The information that you can view about an asset and the actions that you can perform on an asset
vary by asset type. A few actions apply to all asset types, for example, you can create, edit the
properties of, and remove or delete all types of assets. You can edit the contents of most types of
assets in projects. For data assets that contain relational data, you can shape and cleanse the data
with the Data Refinery tool. For analytical assets, you can edit the contents in the appropriate editor
tool. In catalogs, you can edit only the metadata for the asset.
A new project has no assets. By default, the Data assets type is added with all project starters. To
add other asset types to your project click Add to project.

© Copyright IBM Corp. 2018, 2019 3-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
For more information, see About assets at
https://dataplatform.cloud.ibm.com/docs/content/getting-started/assets.html?audience=wdp&conte
xt=analytics

© Copyright IBM Corp. 2018, 2019 3-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Communities
• Articles: Curated articles of interests to data scientists
• Data sets: Multiple open source data sets, including local, state, and
government data
• Notebooks and tutorials:
ƒ Example notebooks
ƒ Notebook tutorials about how to perform specific use cases and access
different data sources

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-19. Communities

Watson Studio communities are a place where you can find articles of interests for data scientist.
These are external articles that you can peruse. Within the Watson Studio communities, you can
also find and use open data sets that are ready to use, including local, state, and government data.
You download the data set and load it into your project. If you are working within a notebook, you
can add the data set to the project. Communities are a great place to get started if you are exploring
the data science space. There are sample notebooks and tutorials to get you started or to learn
about new libraries and use cases.

© Copyright IBM Corp. 2018, 2019 3-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Collaborating in a project
• Project collaborators share knowledge and resources.
• Admin role is required to manage collaborators (add, remove, and edit).
• Collaborators are added at the project level.
• Only collaborators in a project can access the project’s data and
notebooks assets.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-20. Collaborating in a project

After you create a project, add collaborators to share knowledge and resources. Project
collaborators share knowledge and resources and help one another complete jobs. You must have
the Admin role in the project to manage collaborators.
Only the collaborators in your project can access your data, notebooks and other assets.
Collaborators can be removed from a project or have their permissions changes.
To add collaborators to your project:
1. From your project, click the Access Control tab, and then click Add collaborators.
2. Add the collaborators who you want to have the same access level:
▪ Type email addresses into the Invite field.
▪ Copy multiple email addresses, separated by commas, and paste them into the Invite field.
3. Choose the access level for the collaborators and click Add:
▪ Viewer: View the project.
▪ Editor: Control project assets.
▪ Admin: Control project assets, collaborators, and settings.
4. Add more collaborators with the same or different access levels.

© Copyright IBM Corp. 2018, 2019 3-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
5. Click Invite.
If the invited users have existing IBM Cloud accounts with Watson Studio activated, they are added
to your project immediately.
If an invited user does not have a IBM Cloud account, the user receives an email invitation to create
a IBM Cloud account and activate Watson Studio. When the user activates Watson Studio, the user
can see your project and the user's status on your collaborators list changes
from Invited to Active. If necessary, you can resend or cancel an invitation.
For more information, see Project collaborators at
https://dataplatform.cloud.ibm.com/docs/content/getting-started/collaborate.html?context=analytics

© Copyright IBM Corp. 2018, 2019 3-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Watson Studio and Spark

• Apache Spark is an open-source distributed general-purpose cluster-
computing framework:
ƒ Provides a core data processing engine.
ƒ Libraries for SQL, machine learning, graph computation, and stream
processing run on Spark and can be used together in an application.
• You need a Spark service or Spark environment if:
ƒ Your notebook includes Spark APIs.
ƒ You create machine learning models or model flows with Spark runtimes.
• Spark options in Watson Studio:
ƒ Spark environments offered under Watson Studio.
ƒ Spark services offered through IBM Cloud.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-21. Watson Studio and Spark

Apache Spark is an open source distributed cluster computing framework optimized for extremely
fast and large scale data processing. Spark provides a core data processing engine. Several
libraries for SQL, machine learning, graph computation, and stream processing run on Spark and
can be used together in an application. To learn more about Apache Spark, see documentation and
examples at spark.apache.org.
If your notebook includes Spark APIs, or you create machine learning models or model flows with
Spark runtimes, you need to associate the tool with a Spark service or environment. With Spark
environments, you can configure the size of the Spark driver and the size and number of the
executors. You can use Spark environments for notebooks, the model builder and Spark modeler
flows.

© Copyright IBM Corp. 2018, 2019 3-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
Spark options
In Watson Studio, you can use:
• Spark environments offered under Watson Studio
All Watson Studio users can create Spark environments with varying hardware and software
configurations. Spark environments offer Spark kernels as a service (SparkR, PySpark and
Scala). Each kernel gets a dedicated Spark cluster and Spark executors. Spark environments
are offered under Watson Studio and, like default environments, consume capacity unit hours
(CUHs) that are tracked.
• Spark services offered through IBM Cloud
You can add the Spark service to your project. Spark is a fast, in-memory engine for very large
data sets. In Watson Studio, you can use the Apache Spark service for your Python, Scala, or R
notebooks.

© Copyright IBM Corp. 2018, 2019 3-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Spark default environments

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-22. Spark default environments

Spark environments offered under Watson Studio

All Watson Studio users can create Spark environments with varying hardware and software
configurations. Spark environments offer Spark kernels as a service (SparkR, PySpark and Scala).
Each kernel gets a dedicated Spark cluster and Spark executors. Spark environments are offered
under Watson Studio and, like default environments, consume capacity unit hours (CUHs) that are
tracked.
The slide shows the default Spark environments definition under the project’s Environment tab.

© Copyright IBM Corp. 2018, 2019 3-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Associating a Spark service

• Click Studio project > Settings > Associated services > Add service.

• Create Spark service instance

• Spark service added to Watson Studio project

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-23. Associating a Spark service

Spark services offered through IBM Cloud

You can add the Spark service to your project:
1. Select the Settings tab.
2. Scroll-down to Associated services.
3. Click Add service.
4. Select Spark.
5. Create the Spark service instance.
6. The service is listed in the Associated services section.
The slide shows the main screen captures in the steps listed above.

© Copyright IBM Corp. 2018, 2019 3-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
3.3. Jupyter notebook

© Copyright IBM Corp. 2018, 2019 3-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Jupyter notebook

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-24. Jupyter notebook

© Copyright IBM Corp. 2018, 2019 3-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Topics
• Watson Studio overview
• Watson Studio components
• Jupyter notebook

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-25. Topics

© Copyright IBM Corp. 2018, 2019 3-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Jupyter notebooks overview

• A web-based environment where
you can run small pieces of code
that process your data and
immediately visualize the results.
• Include all the building blocks to
work with data:
ƒ The data
ƒ The code computations that
process the data
ƒ Visualizations of the results
ƒ Text and rich media to enhance
understanding
• Other options:
ƒ Zeppelin notebooks (Watson Studio
Local)
ƒ Rstudio for statistical computing

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-26. Jupyter notebooks overview

A Jupyter notebook is a web-based environment for interactive computing. You can run small
pieces of code that process your data, and you can immediately view the results of your
computation. Notebooks include all of the building blocks you need to work with data:
• The data
• The code computations that process the data
• Visualizations of the results
• Text and rich media to enhance understanding
From markdown and live code to visualizations, notebooks include all of the building blocks you
need to work with data and enhance your understanding.
You can uses notebooks to add formatted text around executable code to describe what is being
done and show the result, including graphics, concurrently.

© Copyright IBM Corp. 2018, 2019 3-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
There are a few popular notebooks, including the Jupyter Notebook, which is popular with Python
programmers because Python is popular with data scientists.
Other notebooks can be added over time. For example, Watson Studio Local added another
popular notebook that is called Zeppelin.
Another popular environment for data science, statistical analysis, and graphic representation is
provided by the R language. Watson Studio includes RStudio for people that prefer the R
development environment.

© Copyright IBM Corp. 2018, 2019 3-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Parts of a notebook
• Menu bar and toolbar

• Action bar

• Cells in a Jupyter Notebook:

ƒ Code cells
ƒ Markdown cells

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-27. Parts of a notebook

The menu bar controls most of the operations and settings for the notebook. Simple and common
functions are supported through the menu bar.
From the action bar you can select features that enhance notebook collaboration. From the action
bar, you can:
• Publish your notebook as a gist or to GitHub.
• Create a permanent URL so that anyone with the link can view your notebook.
• Schedule to run your notebook at a given time.
• Add a project token so that code can access the project resources.
• View your notebook information. Change the name of your notebook by editing it in
the Name field. If your notebook runs in an environment, you can view the environment details
and runtime status.
• Save versions of your notebook.
• View and add data sources.
• Post comments to project collaborators.

© Copyright IBM Corp. 2018, 2019 3-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
• Integrate data into your notebook.
• Find resources in the community, for example, useful data sets.
Cells in a Jupyter notebook
A Jupyter notebook consists of a sequence of cells. The flow of a notebook is sequential. You enter
code into an input cell, and when you run the cell, the notebook executes the code and prints the
output of the computation to an output cell.
You can change the code in an input cell and re-run the cell as often as you like. In this way, the
notebook follows a read-evaluate-print loop paradigm. You can choose to use tags to describe cells
in a notebook.
The behavior of a cell is determined by a cell’s type. The types of cells include:
• Code cells: They are the cells where you edit and run the code. The output of the cell appears
beneath the cell. Tags can be used to describe the cell for code readability and maintainability.
Cells can be rerun as often as you like.
• Markdown cells are used to document and comment the process. You can use this to structure
your notebook by using the markdown language. Images and file attachments can be added to
the notebook by using the markdown cells.

© Copyright IBM Corp. 2018, 2019 3-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Creating notebooks
• Must have a project and a Spark instance.
ƒ Associate with existing Spark instance or create a new instance.
• Options to create a Jupyter notebook:
ƒ Blank, From a file, From a URL
ƒ Copy sample notebook from the community
• Specify a name for the notebook.
• Specify the language:
ƒ Python 2
ƒR
ƒ Scala
ƒ Python 3.5 (experimental)
• Specify the Spark version:
ƒ 2.1, 2.0, 1.6
Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-28. Creating notebooks

Before you can create a notebook, you must have a project and associate a Spark instance with it.
If you already have an existing Spark instance, you may use it. Otherwise, you must create a Spark
instance.
When the project is set up, you can create the notebook by using one of these ways:
• Blank
• From a file
• From a URL
You must specify a name for your notebook. If you have a blank notebook, you must specify the
language and the Spark version that you want to use with the notebook. You can create a notebook
by importing a Python, Scala, or R notebook file (.ipynb) from your local workstation. You can also
create a notebook from a URL by providing the URL.
Alternatively, you can copy a sample notebook from the Community to help you get started.

© Copyright IBM Corp. 2018, 2019 3-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Creating notebooks (cont.)

• From the project, click Add to project > Notebook > New notebook.
ƒ Select an option: Blank, From file, or From URL.

• Copy sample from Community.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-29. Creating notebooks (cont.)

Create a notebook file

To create a notebook file in the project:
1. From your project, click Add to Project > Notebook.
2. On the New Notebook page, specify the method to use to create your notebook. You can
create a blank notebook, upload a notebook file from your file system, or upload a notebook file
from a URL. The notebook you create or select must be a .ipynb file.
3. Specify the language: Python, R, or Scala.
4. Specify the runtime environment. After you have created an environment definition on
the Environments page of your project, it will appear in the list of runtimes you can select from
at the time you create the notebook.
5. Click Create Notebook. The notebook opens in edit mode.

© Copyright IBM Corp. 2018, 2019 3-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
Copy a sample notebook from the Community
Sample notebooks from the Community are based on real-world scenarios and contain many
useful examples of computations and visualizations that you can adapt to your analysis needs.
To copy a sample notebook:
1. Click Community from the Watson Studio toolbar, then filter for Notebooks to show only
notebook cards.
2. Find the card for the sample notebook you want and click the card. You can view the notebook
contents to browse the steps and the code that it contains.
3. To work with a copy of the sample notebook, click the Copy icon. The New Notebook screen
opens.
4. Choose the project for the notebook.
5. Specify the runtime environment. After you have created an environment definition on
the Environments page of your project, it will appear in the list of runtimes you can select from
at the time you create the notebook.
6. Click Create Notebook. The notebook opens in edit mode.

© Copyright IBM Corp. 2018, 2019 3-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Coding and running notebooks

• Import libraries:
ƒ Preinstalled from Python or R.
ƒ Install custom or third-party libraries for any language. For Scala, no libraries
are preinstalled in the Spark service.
• Load and access data:
ƒ Add a file from the local system to your object store.
ƒ Use a free data set from the Watson Studio home page.
ƒ Load data from a data source connection.
• Prepare and analyze the data.
• Collaborate with other project members or share outside Watson
Studio.
• Visualize the results.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-30. Coding and running notebooks

To code and run notebooks, complete the following steps:

1. Import the libraries that you need for the notebook. You can import preinstalled libraries if you
are using Python or R. If you are using Scala, you must install the libraries manually, and they
are available for the duration of that notebook.
2. Load and access the data. To load data into your own notebooks, you can choose one of these
options:
▪ Add a file from your local system to your object storage.
▪ Use a free data set from the community.
▪ Load data from a data source connection, such as an external data source or another IBM
Cloud service.
3. Prepare and analyze data
With the libraries and data loaded, you can start data analysis by preparing the data, analyzing
the data, and making predictions. You can write your own code with Python functions to work
with data and IBM Cloud Object Storage in notebooks.

© Copyright IBM Corp. 2018, 2019 3-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
4. Collaborate with other project members and share your notebook with people outside Watson
Studio.
You can create a URL to share the last saved version of a notebook on social media or with
people outside of Watson Studio. The URL shows a read-only view of the notebook. Anyone
who has the URL can view or download the notebook. Whenever you save a new version of the
notebook with the File > Save Version command, the URL shows the new version. The shared
notebook shows the author of the shared version and when the notebook version was last
updated.
5. Visualize the data. Use visualizations in your notebooks to present data visually to help identify
patterns, gain insights, and make decisions. Many of your favorite open source visualization
libraries, such as matplotlib, are pre-installed on Watson Studio. All you have to do is import
them. In the upcoming exercise, you use visualization libraries such as PixieDust to visualize
your data.

© Copyright IBM Corp. 2018, 2019 3-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Unit summary
• Describe Watson Studio.
• Identify industry use cases.
• List Watson Studio offerings.
• Create Watson Studio projects.
• Describe Watson Studio and Spark.
• Describe Watson Studio and Object Storage.
• Explain Watson Studio high availability considerations.
• Prepare and analyze data.
• Use Jupyter notebooks.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-31. Unit summary

© Copyright IBM Corp. 2018, 2019 3-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Review questions
1. True or false: Watson Studio is designed only for the data
scientist persona.

2. True or false: Object storage provides the space where

unstructured data for your project is stored.

3. True or false: Collaborators can be given different access

levels.

4. True or false: Collaboration within Watson Studio is an

optional add-on component that must be purchased.

5. True or false: Watson Studio communities provide access to

articles, tutorials, and even data sets that you can use.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-32. Review questions

© Copyright IBM Corp. 2018, 2019 3-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Review answers
1. True or false: Watson Studio is designed only for the data
scientist persona.

2. True or false: Object storage provides the space where

unstructured data for your project is stored.

3. True or false: Collaborators can be given different access

levels.

4. True or false: Collaboration within Watson Studio is an

optional add-on component that must be purchased.

5. True or false: Watson Studio communities provide access to

articles, tutorials, and even data sets that you can use.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-33. Review answers

1. True or false: Watson Studio is designed only for the data scientist persona.
False: “The data engineer, the data scientist, the business analyst, and the app developer.
Each persona has primary tools that help them do their job. For example, the data scientist's
main tool is Watson Studio but other personas can use it as it relates to their jobs. . Also, there
might be a team of different personas. Whatever the case is, you must decide what tool is
correct for the job, regardless of the personas. The definitions of personas can vary between
different companies and evolve over time.”
2. True or false: Object storage provides the space where unstructured data for your project is
stored.
True: “An IBM Cloud Object Storage instance can be created at project creation time or a new
project can be associated with an existing Cloud Object Storage instance.”
3. True or false: Collaborators can be given certain access levels.
True: “Add collaborators to your project by using their email addresses. If they have an existing
account on IBM Cloud, they are added immediately. Otherwise, they receive an invite to create
a Watson Studio account. Choose the permissions for each collaborator. The Admin role can
control project assets, collaborators, and settings. The Editor role can control project assets.
The Viewer role can view the project. Collaborators can be removed from a project or have their
permissions updated.”

© Copyright IBM Corp. 2018, 2019 3-49

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty
4. True or false: Collaboration within Watson Studio is an optional add-on component that must be
purchased.
False: “Collaboration is a standard feature in Watson Studio.”
5. Watson Studio communities provide access to articles, tutorials, and even data sets that you
can use.
True: “Watson Studio communities are a place where you can find articles of interests for data
scientist. These are external articles that you can peruse. Within the Watson Studio
communities, you can also find and use open data sets that are ready to use, including local,
state, and government data. You download the data set and load it into your project. If you are
working within a notebook, you can add the data set to the project. Communities are a great
place to get started if you are exploring the data science space. There are sample notebooks
and tutorials to get you started or to learn about new libraries and use cases.”

© Copyright IBM Corp. 2018, 2019 3-50

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Exercise: Getting started with

Watson Studio

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-34. Exercise: Getting started with Watson Studio

© Copyright IBM Corp. 2018, 2019 3-51

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 3. Introduction to IBM Watson Studio

Uempty

Exercise objectives
• This exercise introduces you to the basic tasks that you will
perform when using Watson Studio.
• After completing this exercise, you should be able to:
ƒ Create a Watson Studio project.
ƒ Manage the project.
ƒ Assign collaborators.
ƒ Load a data set into the project’s object store.
ƒ Manage Cloud Object Storage.
ƒ Analyze data by using Watson Studio.
ƒ Use PixieDust for data visualization.

Introduction to IBM Watson Studio © Copyright IBM Corporation 2019

Figure 3-35. Exercise objectives

© Copyright IBM Corp. 2018, 2019 3-52

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Unit 4. Introduction to IBM Watson

Machine Learning
Estimated time
00:30

Overview
This unit describes the CRoss Industry Standard Process for Data Mining (CRISP-DM) and
explains the process of preparing data for a machine learning algorithm. This unit provides an
overview of the IBM Watson Machine Learning service available on IBM Cloud.

© Copyright IBM Corp. 2018, 2019 4-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Unit objectives
• Describe the Cross-Industry Standard Process for Data Mining (CRISP-
DM) process model.
• Explain where machine learning fits in the CRISP-DM process.
• Describe data preparation before feeding into machine learning
algorithms.
• Describe Watson Machine Learning features and capabilities.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 4-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
4.1. Cross-Industry Standard Process for Data
Mining

© Copyright IBM Corp. 2018, 2019 4-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Cross-Industry Standard
Process for Data Mining

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-2. Cross-Industry Standard Process for Data Mining

© Copyright IBM Corp. 2018, 2019 4-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Topics
• Cross-Industry Standard Process for Data Mining
• Data preparation
• Watson Machine Learning

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-3. Topics

© Copyright IBM Corp. 2018, 2019 4-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Cross-Industry Standard Process for Data Mining overview

• CRISP-DM stands for Cross-Industry Standard Process for Data
Mining.
• It is an open standard guide that describes common approaches that
are used by data mining experts.
• As a methodology, CRISP-DM includes descriptions of the typical
phases of a project, including tasks details.
• As a process model, CRISP-DM provides an overview of the data
mining lifecycle.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-4. Cross-Industry Standard Process for Data Mining overview

CRISP-DM is an industry-proven way to guide your data mining efforts. It is the most widely used
analytics model. It describes common approaches that are used by data mining experts.
As a methodology, it includes descriptions of the typical phases of a project, the tasks that are
involved with each phase, and an explanation of the relationships between these tasks.
As a process model, CRISP-DM provides an overview of the data mining lifecycle. In a nutshell, it
consolidates preferred practices.
Reference:
https://www.ibm.com/support/knowledgecenter/en/SS3RA7_15.0.0/com.ibm.spss.crispdm.help/cris
p_overview.htm

© Copyright IBM Corp. 2018, 2019 4-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

CRISP-DM lifecycle

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-5. CRISP-DM lifecycle

The lifecycle model consists of six phases with arrows indicating the most important and frequent
dependencies between phases. The sequence of the phases is not strict. In fact, most projects
move back and forth between phases as necessary.
It starts with business understanding, and then moves to data understanding, data preparation,
modelling, evaluation, and deployment.
The CRISP-DM model is flexible and can be customized easily. For example, if your organization
aims to detect money laundering, it is likely that you examine large amounts of data without a
specific modelling goal. Instead of modelling, your work focuses on data exploration and
visualization to uncover suspicious patterns in financial data.
In such a situation, the modelling, evaluation, and deployment phases might be less relevant than
the data understanding and preparation phases. However, it is still important to consider some of
the questions that are raised during these later phases for long-term planning and future data
mining goals.
Reference:
https://www.ibm.com/support/knowledgecenter/en/SS3RA7_15.0.0/com.ibm.spss.crispdm.help/cris
p_overview.htm

© Copyright IBM Corp. 2018, 2019 4-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Phases in CRISP-DM

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-6. Phases in CRISP-DM

This slide summarizes the tasks and outcomes of each phase.

© Copyright IBM Corp. 2018, 2019 4-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
4.2. Data preparation

© Copyright IBM Corp. 2018, 2019 4-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data preparation

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-7. Data preparation

© Copyright IBM Corp. 2018, 2019 4-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Topics
• Cross-Industry Standard Process for Data Mining
• Data preparation
• Watson Machine Learning

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-8. Topics

© Copyright IBM Corp. 2018, 2019 4-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data preparation
The process of preparing data for a machine learning algorithm has the
following phases:
• Data selection
• Data preprocessing
• Data transformation

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-9. Data preparation

Machine learning algorithms depend highly on the quality and quantity of data. It is important that
you provide these algorithms the correct data. Data preparation is a large subject that can involve
many iterations, exploration, and analysis. Becoming proficient at data preparation will make you a
master at machine learning.
In this section, we cover basics tasks of the data preparation process: data selection, data
preprocessing, and data transformation.
References:
https://www.simplilearn.com/data-preprocessing-tutorial
https://machinelearningmastery.com/how-to-prepare-data-for-machine-learning/

© Copyright IBM Corp. 2018, 2019 4-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data selection
Think about:
• What data is available, what data is missing, and what data can be removed?
• Is the selected sample an accurate representation of the entire population?
• Is more data better?

Banko and Brill [2001] http://www.aclweb.org/anthology/P01-1005

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-10. Data selection

This step is concerned with selecting a subset of all the available data with which you are working.
Consider what data is available, what data is missing, and what data can be removed.
Make some assumptions about the data that you require and record those assumptions. Ask
yourself:
• What data is available? For example, through which media, such as database tables or other
systems? Is it structured or unstructured? Make sure that you are aware of everything that you
can use.
• What data is not available and you want to get? For example, data that is not or cannot be
recorded. Can you develop or simulate this data?
• What data can be removed (because it does not address the problem)? Document which data
you excluded and why.
It is common to think that the more data we have the better result we get, but this is not necessarily
true. According to the paper "Scaling to Very Very Large Corpora for Natural Language
Disambiguation" by Microsoft Researchers Banko and Brill [2001] [1]. They proved that for a given
problem, different algorithms perform virtually the same and the accuracy increases when adding
more data (in this case, words). But, for large amounts of data, the improvements start to become
negligible.

© Copyright IBM Corp. 2018, 2019 4-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
References:
[1]http://www.aclweb.org/anthology/P01-1005
https://www.dummies.com/programming/big-data/phase-3-of-the-crisp-dm-process-model-data-pre
paration/
https://www.simplilearn.com/data-preprocessing-tutorial
https://machinelearningmastery.com/how-to-prepare-data-for-machine-learning/

© Copyright IBM Corp. 2018, 2019 4-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data selection: Samples selection

Selecting the right size of the sample is a key step in data preparation.
Samples that are too large or too small might give skewed results.
• Sampling Noise
• Sampling Bias

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-11. Data selection: Samples selection

Selecting the correct size of the sample is a key step in data preparation. Samples that are too
large or too small might give skewed results.
Sampling Noise: Smaller samples cause sampling noise because they are trained on
non-representative data.
Sampling Bias: A sample is biased if certain samples are underrepresented or overrepresented
relative to others in the population. Larger samples work well if there is no sampling bias, that is,
when the correct data is picked.
Reference:
https://www.simplilearn.com/data-preprocessing-tutorial

© Copyright IBM Corp. 2018, 2019 4-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data selection: Survey sampling

• Undercoverage
• Non-response bias
• Voluntary response bias

Unrepresentative
Samples
Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-12. Data selection: Survey sampling

A good sample is representative, meaning that each sample point represents the attributes of a
known number of population elements. The bias that results from an unrepresentative sample is
called selection bias. There are various types of bias in survey like Undercoverage, Non-response
bias and voluntary response bias. To explain these types assume that you would like to conduct a
survey about customers and their purchase preferences.
• Undercoverage: Undercoverage occurs when some members of the population are
inadequately represented in the sample. For example, when a minority is underrepresented in a
sample, this situation can affect the validity of the sample. In this example, assume that you
underrepresented the customers who have a low income.
• Non-response bias: Sometimes, members that are chosen for the sample are unwilling or
unable to participate in the survey. Non-response bias is the bias that results when respondents
differ in meaningful ways from non-respondents. This bias can affect the validity of the sample.
Non-response bias is a common problem with mail surveys because the response rate is
often low, making mail surveys vulnerable to non-response bias.
• Voluntary response bias: This bias occurs when sample members are
self-selected volunteers, as in voluntary samples. When this happens, the resulting sample
tends to over represent individuals who have strong opinions.

© Copyright IBM Corp. 2018, 2019 4-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
References:
https://en.wikipedia.org/wiki/Survey_sampling
https://sites.google.com/site/apstatisticssurveys/bias-in-surveys/bias-due-to-unrepresentative-sam
ples

© Copyright IBM Corp. 2018, 2019 4-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data preprocessing: Overview

• Data challenges:
ƒ Noise and outliers
ƒ Missing values
ƒ Inconsistent values
ƒ Duplicate data

• Data preprocessing is a data mining technique that involves

transforming raw data into an understandable format.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-13. Data preprocessing: Overview

Why we use data preprocessing

In actual scenarios, data is generally incomplete:
• Data might lack attribute values, lacking certain attributes of interest.
• Data is noisy that contains errors or outliers. For example, human height as a negative value.
• Data might be inconsistent, containing discrepancies in codes or names. For example, a record
for two employees having the same ID.
We usually come across much raw data that is not fit to be readily processed by machine learning
algorithms. We must preprocess the raw data before it is fed into various machine learning
algorithms. Organize your selected data by formatting, cleaning, and sampling from the data. Poor
data quality negatively affects many data processing efforts.
References:
https://hackernoon.com/what-steps-should-one-take-while-doing-data-preprocessing-502c993e1caa
https://medium.com/datadriveninvestor/machine-learning-ml-data-preprocessing-5b346766fc48
https://machinelearningmastery.com/how-to-prepare-data-for-machine-learning/

© Copyright IBM Corp. 2018, 2019 4-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data preprocessing: Steps overview

1. Data cleaning: Complete missing values, smooth noisy data, identify

or remove outliers, and resolve inconsistencies.
2. Data integration: Using multiple databases, other data sources, or
files.
3. Data sampling: Faster for exploring and prototyping.
4. Data dimensionality reduction: Reducing the volume but producing
the same or similar analytical results.
5. Data formatting: The data that you selected might not be in a format
that is suitable for you to use.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-14. Data preprocessing: Steps overview

The following list summarizes the steps that are used in preprocessing data:
1. Data cleaning: Complete missing values, smooth noisy data, identify or remove outliers, and
resolve inconsistencies.
2. Data integration: Using multiple databases, other data sources, or files.
3. Data sampling: You can take a smaller representative sample of the selected data that might
be much faster for exploring and prototyping solutions before considering the whole data set.
4. Data dimensionality reduction: Reducing the dimensions of the data and producing the same
or similar analytical results. This is a kind of data compression that uses less memory or disk
space and speeds the learning algorithm. For example, assume that you have a feature for size
in centimeters and another feature for size in inches. By removing one of those redundant
features, you reduce the dimensions of your data from 3D to 2D.
5. Data formatting: The data that you selected might not be in a format that is suitable for you to
use. For example: the data might be in a relational database and you want it in a
comma-separated file.
References:
https://medium.com/datadriveninvestor/machine-learning-ml-data-preprocessing-5b346766fc48
https://machinelearningmastery.com/how-to-prepare-data-for-machine-learning/

© Copyright IBM Corp. 2018, 2019 4-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Data preprocessing: Steps overview (cont.)

• Data transformation:
ƒ Scaling
ƒ Aggregation
ƒ Decomposition

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-15. Data preprocessing: Steps overview (cont.)

Data transformation (also called feature engineering) is a set of actions that covers transformation
of the processed data. Engineering features from your data can use some time, but they can
enhance the machine learning performance. There are three common data transformations:
• Scaling: The pre-processed data may contain attributes with a mixture of scales for various
quantities, such as meters, grams, and dollars. The features should have the same scale, for
example, 0 (smallest value) to 1 (largest value).
• Aggregation: There may be features that can be aggregated into a single feature, which is
more meaningful to the problem that you are trying to solve.
• Decomposition: There may be complex features where it is more useful to split into parts. For
example, a feature representing a date and time stamp in a long format can be split out further
into only the hour of the day. Think about what your problem really needs.
References:
https://medium.com/datadriveninvestor/machine-learning-ml-data-preprocessing-5b346766fc48
https://machinelearningmastery.com/how-to-prepare-data-for-machine-learning/

© Copyright IBM Corp. 2018, 2019 4-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
4.3. Watson Machine Learning

© Copyright IBM Corp. 2018, 2019 4-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-16. Watson Machine Learning

© Copyright IBM Corp. 2018, 2019 4-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Topics
• Cross-Industry Standard Process for Data Mining
• Data preparation
• Watson Machine Learning

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-17. Topics

© Copyright IBM Corp. 2018, 2019 4-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning

• Watson Machine Learning is a service on IBM Cloud with features for
training and deploying machine learning models and neural networks.
• Watson Machine Learning is integrated with IBM Watson Studio.
• Enables users to perform two fundamental operations of machine
learning: training and scoring.
ƒ Training is the process of refining an algorithm so that it can learn
from a data set.
ƒ Scoring is the operation of predicting an outcome by using a trained
model.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-18. Watson Machine Learning

Machine Learning is a service on IBM Cloud with features for training and deploying machine
learning models and neural networks. To design, train, and deploy machine learning models in IBM
Watson Studio, you must associate an IBM Watson Machine Learning service instance and
supporting services (such as IBM Cloud Object Storage) with a project.
Machine Learning enables users to perform two fundamental operations of machine learning:
training and scoring.
• Training is the process of refining an algorithm so that it can learn from a data set. The output
of this operation is called a model. A model encompasses the learned coefficients of
mathematical expressions.
• Scoring is the operation of predicting an outcome by using a trained model. The output of the
scoring operation is another data set containing predicted values.
References:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-overview.html
https://console.bluemix.net/docs/services/PredictiveModeling/index.html#WMLgettingstarted

© Copyright IBM Corp. 2018, 2019 4-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning features

• Interfaces for building, training, and deploying models:
• Python client library external link
• Command-line interface (CLI)
• REST API external link
• Deployment infrastructure
• Distributed deep learning
• GPUs for faster training

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-19. Watson Machine Learning features

The Machine Learning service provides the following features:

• Interfaces for building, training, and deploying models: a Python client library external link, CLI,
and a REST API external link.
• Deployment infrastructure for hosting your trained models. Although training is a critical step in
the machine learning process, Machine Learning enables you to streamline the functioning of
your models by deploying them and getting business value from them over time and through all
of their iterations.
• Distributed deep learning for distributing training runs across multiple servers.
• GPUs for faster training.
References:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-overview.html
https://console.bluemix.net/docs/services/PredictiveModeling/index.html#WMLgettingstarted

© Copyright IBM Corp. 2018, 2019 4-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning personas

• Data scientists:
ƒ Use data transformations and machine learning algorithms.

ƒ Use notebooks or external tools.

ƒ Often collaborate with data engineers to explore and understand the data.

• Developers build intelligent applications that use the predictions output

of machine learning models.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-20. Watson Machine Learning personas

Data scientists create machine learning pipelines that use data transformations and machine
learning algorithms. They typically use notebooks or external tools to train and evaluate their
models. Data scientists often collaborate with data engineers to explore and understand the data.
Developers build intelligent applications that use the predictions output by machine learning
models.
References:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-overview.html
https://console.bluemix.net/docs/services/PredictiveModeling/index.html#WMLgettingstarted

© Copyright IBM Corp. 2018, 2019 4-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning: Building the model

You can build your model by using one of the following tools (shown on
this and the next slide):
1. Model builder:
ƒ Automatic data preparation
ƒ Technique recommendation
ƒ Manual mode to select the estimator

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-21. Watson Machine Learning: Building the model

There are different tools that you can use to create a machine learning model:
• Model builder.
• Flow editor.
• A notebook to prepare data, train the model, and deploy the model.
You build your model by selecting the data, manipulating the data, and selecting estimators or
algorithms to use for classification. You can transform the data by appending new columns or
mapping existing data to a new column. An estimator trains the data and produces a model, which
you can deploy and use for prediction.
Before you can create a model, you must have an Apache Spark service and a machine learning
service. If you do not already have a machine learning service, you are given a link and directed to
create one during the initial model creation step.
The model builder is step-by-step process that uses a model by using popular machine learning
algorithms. All that you have to do is simply upload your training data, and then let the model
builder automatically prepare your data and recommend techniques that suit your data.

© Copyright IBM Corp. 2018, 2019 4-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
For automatic data preparation, the model builder automatically prepares your training data (in both
automatic mode and manual mode). For example, it extracts the first 1000 records as a data
sample to determine whether string categories exceed the maximum that are allowed. It also
handles missing string values, and defines missing values as a separate category. If the label
column contains strings, the model encodes the label column to a column of indexes and converts
features that are categorical to category indexes.
Technique recommendation
For example, it recommends using a binary classification, multi-classification, or regression.
Manual mode to select an estimator
By using manual mode in the model builder, you can choose one or more specific estimators, such
as linear regression, logistic regression, or a decision tree.
References:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-pipelines.html
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-model-builder.html#data

© Copyright IBM Corp. 2018, 2019 4-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning: Building the model (cont.)

2. Flow Editor (modeler flow):
ƒ Use the Flow Editor to create a machine learning flow.
ƒ Use the Flow Editor to create a deep learning flow.

3. Use a notebook.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-22. Watson Machine Learning: Building the model (cont.)

You can create a machine learning flow, which is a graphical representation of a data model, or a
deep learning flow, which is a graphical representation of a neural network design, by using the
Flow Editor. Use it to prepare or shape data, train or deploy a model, or transform data and export
it back to a database table or file in IBM Cloud Object Storage.
The third tool that you can use to create or use a machine learning model is to use a notebook to
write the code and implement the machine learning API. After a model is created, trained, and
deployed, you can run the deployed model in a notebook.
References:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-canvas.html
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-notebook.html

© Copyright IBM Corp. 2018, 2019 4-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Watson Machine Learning: Deploying the model

• A deployed model is saved to the model repository.
• Deployments methods:
ƒ Deploy a model from a notebook.
ƒ Deploy a model from the Flow Editor.
ƒ Deploy a model from the model builder.
ƒ Deploy a batch or steaming model.

• Continuous learning and automated monitoring of model performance.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-23. Watson Machine Learning: Deploying the model

After you create, train, and evaluate a model, you can deploy it. Although it is possible to score a
model without deploying it, a model must be deployed before it can be scored from the Watson
Machine Learning APIs. Also, a model can have only a single deployment. For a trial account, a
user can have only one deployed model at a time.
When you deploy a model, you save it to the model repository that is associated with your Watson
Machine Learning service. Then, you can use your deployed model to score data and build an
application.
There are different ways to deploy your model:
• Deploy a model from a notebook.
• Deploy a model from the Flow Editor.
• Deploy a model from the model builder.
• Deploy a batch or steaming model.
Because model deployment is not a one-time event, you can use the Machine Learning continuous
learning system, which provides automated monitoring of model performance, retraining, and
redeployment to ensure prediction quality.

© Copyright IBM Corp. 2018, 2019 4-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty
Reference:
https://dataplatform.cloud.ibm.com/docs/content/analyze-data/ml-deploy.html

© Copyright IBM Corp. 2018, 2019 4-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Unit summary
• Describe the Cross-Industry Standard Process for Data Mining (CRISP-
DM) process model.
• Explain where machine learning fits in the CRISP-DM process.
• Describe data preparation before feeding into machine learning
algorithms.
• Describe Watson Machine Learning features and capabilities.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-24. Unit summary

© Copyright IBM Corp. 2018, 2019 4-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review questions
1. In CRISP-DM, which phase focuses on machine learning?
A. Business understanding
B. Data preparation
C. Modeling
D. Evaluation
E. Deployment

2. True or False: Watson Machine Learning integrates with

Watson Studio.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-25. Review questions

1. C: Modeling.
2. True

© Copyright IBM Corp. 2018, 2019 4-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review questions (cont.)

3. The most time-consuming phase in CRISP-DM is:
A. Business understanding
B. Data preparation
C. Evaluation preparation
D. Deployment preparation
4. Which of the following is not part of data processing?
A. Data Cleaning
B. Data prediction
C. Data Integration
D. Data Sampling
E. Data formatting

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-26. Review questions (cont.)

3. B. Data preparation
4. B. Data prediction

© Copyright IBM Corp. 2018, 2019 4-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review questions (cont.)

5. Which of the following are Watson Machine Learning
personas?
A. Data scientist
B. Business analyst
C. Developers
D. Project manager
E. Tester
F. All of the above
G. A & C
H. C & E

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-27. Review questions (cont.)

3. G. A (Data Scientist) and C (Developer)

© Copyright IBM Corp. 2018, 2019 4-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review answers
1. In CRISP-DM, which phase focuses on machine learning?
A. Business understanding
B. Data preparation
C. Modeling
D. Evaluation
E. Deployment

2. True or False: Watson Machine Learning integrates with

Watson Studio.

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-28. Review answers

1. C: Modeling.
2. True

© Copyright IBM Corp. 2018, 2019 4-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review answers (cont.)

3. The most time-consuming phase in CRISP-DM is:
A. Business understanding
B. Data preparation
C. Evaluation preparation
D. Deployment preparation
4. Which of the following is not part of data processing?
A. Data Cleaning
B. Data prediction
C. Data Integration
D. Data Sampling
E. Data formatting

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-29. Review answers (cont.)

3. B. Data preparation
4. B. Data prediction

© Copyright IBM Corp. 2018, 2019 4-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Review answers (cont.)

5. Which of the following are Watson Machine Learning
personas?
A. Data scientist
B. Business analyst
C. Developers
D. Project manager
E. Tester
F. All of the above
G. A & C
H. C & E

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-30. Review answers (cont.)

3. G. A (Data Scientist) and C (Developer)

© Copyright IBM Corp. 2018, 2019 4-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Exercise 4: Getting started

with Watson Machine Learning

Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-31. Exercise 4: Getting started with Watson Machine Learning

© Copyright IBM Corp. 2018, 2019 4-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 4. Introduction to IBM Watson Machine Learning

Uempty

Exercise objectives
• This exercise introduces you to the basic tasks that you have
to perform while building machine learning models for different
algorithms using Watson Machine Learning service and
Watson Studio.
• After completing this exercise, you should be able to:
ƒ Create a machine learning model by using Watson Studio and
Watson Machine Learning.
ƒ Use data sets to train the model.
ƒ Use different estimators to train the machine learning mode, which
represent different machine learning algorithms.
ƒ Deploy machine learning models.
ƒ Evaluate the deployed models.
ƒ Call the deployed models from your applications.
ƒ Test the model with your data.
Introduction to IBM Watson Machine Learning © Copyright IBM Corporation 2019

Figure 4-32. Exercise objectives

After completing this exercise, you should be able to:

• Create a machine learning model by using Watson Studio and Watson Machine Learning.
• Use data sets to train the model.
• Use different estimators to train the machine learning mode, which represent different machine
learning algorithms.
• Deploy machine learning models.
• Evaluate the deployed models.
• Call the deployed models from your applications.
• Test the model with your data.

© Copyright IBM Corp. 2018, 2019 4-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Unit 5. Introduction to natural language

processing
Estimated time
00:30

Overview
This unit introduces Natural Language Processing. It covers key applications of NLP, basics
concepts and terminology, tools and services and NLP challenges.

© Copyright IBM Corp. 2018, 2019 5-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Unit objectives
• Explain what natural language processing is.
• Identify NLP use cases.
• Explain basic NLP concepts and terminology.
• List the tools and services for NLP.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 5-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty
5.1. Natural language processing overview

© Copyright IBM Corp. 2018, 2019 5-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing

overview

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-2. Natural language processing overview

© Copyright IBM Corp. 2018, 2019 5-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Topics
• Natural language processing overview
• Natural language processing use cases
• Natural language processing basic concepts and terminology
• Natural language processing tools and services

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-3. Topics

© Copyright IBM Corp. 2018, 2019 5-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

What is natural language processing

• NLP is the study of the computational treatment of natural (human)
language.
• It enables machines to understand human communication to extract
different information.
• Examples of NLP applications: Analysis of text in emails, human
speech, social media, or optical character recognition (OCR) from
documents (text that is scanned from actual documents).
• NLP has its origins in machine translation from the 1950s.
• NLP advanced over the years by combining the power of artificial
intelligence (AI), computational linguistics, and computer science.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-4. What is natural language processing

NLP stands for natural language processing. It is a subfield of computer science and AI concerned
with the processing human language by computers. It is one of the most important fields in
computer science in both industry and academia.
NLP enables machines to understand human communication to extract different information.
Examples of NLP applications include analysis of text in emails, human speech, social media, or
optical character recognition (OCR) from documents (text that is scanned from actual documents).
NLP has its origins in machine translation from the 1950s.
The first machine translation was from English to Russian and vice versa, but with poor and
inaccurate results.
Machine translation and other NLP applications advanced over the years by combining the power
of artificial intelligence (AI), computational linguistics, and computer science.

© Copyright IBM Corp. 2018, 2019 5-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing applications

• Machine translation
• Information retrieval: Search engines
• Spell checkers
• Natural language assistants

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-5. Natural language processing applications

Here are the most popular NLP tasks:

• Machine translation: Automatically translating one language to another
• Information retrieval: Search engines, such as Google and Bing
• Spell checkers
• Natural language assistants, such as Siri and Alexa

© Copyright IBM Corp. 2018, 2019 5-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing challenges

• Domains: Higher accuracy for specific domains compared to generic
domains.
• Language: English gets the most attention because it is an
international language.
• Medium: Processing speech is more difficult than processing text.
You can understand your NLP problem by focusing on the following
areas:
• Become familiar with your data.
• Understand the challenges of your particular use case.
• Review the state-of-the-art solutions and technologies for similar
problems.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-6. Natural language processing challenges

There are always some challenges that need to be tackled for any case. In NLP, here are the most
popular challenges:
• Domains: Higher accuracy for specific domains compared to generic domains.
• Language: English gets the most attention because it is an international language.
• Medium: Processing speech is more difficult than processing text.
To resolve some of these challenges, you must become familiar with your data and understand the
challenges of your particular use case. Think about how you will acquire the data and how to
validate its quality. Think about the deployment of your solution and how you are planning to cover
all these points.
Finally, review the state-of-the-art solutions and technologies for similar problems and how these
issues were resolved.

© Copyright IBM Corp. 2018, 2019 5-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty
5.2. Natural language processing use cases

© Copyright IBM Corp. 2018, 2019 5-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing

use cases

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-7. Natural language processing use cases

© Copyright IBM Corp. 2018, 2019 5-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Topics
• Natural language processing overview
• Natural language processing use cases
• Natural language processing basic concepts and terminology
• Natural language processing tools and services

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-8. Topics

© Copyright IBM Corp. 2018, 2019 5-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing use cases

Information extraction
• Goal: Parse the input text to extract valuable output.
ƒ Examples: Entity extraction, relation identification extraction, text
summarization

• Unstructured text: Dynamic structure (for example emails, newspaper

articles, and user reviews).
• Structured text: Defined structure (for example, a database table).

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-9. Natural language processing use cases

NLP technology can be used to extracting information from unstructured text such as emails,
newspaper articles, and user reviews into structured text.
Entity extraction refers to extracting entities from the text such as organizations, people, locations
and so on. For example, the World Health Organization, IBM, Sara, John, Paris, US.
Relation extraction refers to identifying the relationship between entities, for example, “Abraham
Lincoln was a US president”; “Ginni Rometty is the CEO of IBM”.
Text summarization refers to the technique of shortening long pieces of text. Automatic text
summarization is a common use case in machine learning and natural language processing.
Structured text mostly takes the form of tables or values in a structured form.
The goal of information extraction is to parse the incoming text, identify important mentions and
their relations, and extract valuable output into structured text. Doing so can be used to automate
the process of reading articles and passages to convert this information into a structured format.
Computer systems can then manage this information and take proper actions.

© Copyright IBM Corp. 2018, 2019 5-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing use cases (cont.)

Sentiment analysis
• The process of identifying emotions or opinions that are expressed in
user input.
• This analysis is used in marketing, retention plans, and emotional
intelligence for chatbots.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-10. Natural language processing use cases (cont.)

Sentiment analysis is the process of identifying emotions or opinions that are expressed in user
input.
Sentiment analysis answers various questions, such as how people feel about your product or
whether your customers are satisfied with your customer service.
It is used in marketing and retention plans, and emotional intelligence for chatbots, that is, it
enables chatbots to direct the conversation.
Machine learning algorithms brought many advances to this field and are still improving.

© Copyright IBM Corp. 2018, 2019 5-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing use cases (cont.)

• Question and answering: Building solutions that can answer
questions that are asked by humans in natural language.
ƒ Examples: Natural language questions used to retrieve answers from
forums; FAQ application; chatbots

• Speech recognition: Converts spoken language into text.

ƒ Example: Chatbot interactive talk

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-11. Natural language processing use cases (cont.)

Question and answering

Building solutions that can answer questions that are asked by humans in natural language. A
question and answering system can be used for the following tasks:
• Retrieving answers from forums.
• Building a Frequently Asked Questions (FAQs) system.
• Training chatbots
Speech recognition is another use case that helps advancing the capabilities of many different
applications. It converts spoken language into text. It can be used in many applications in several
domains, such as having an interactive talk with a chatbot. It can also be used in Internet of Things
(IoT) applications.

© Copyright IBM Corp. 2018, 2019 5-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty
5.3. Natural language processing basic
concepts and terminology

© Copyright IBM Corp. 2018, 2019 5-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing

basic concepts and
terminology

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-12. Natural language processing basic concepts and terminology

This section introduces basic concepts and terminologies such as synonymy, polysemy, hyponymy,
and hypernymy. The taxonomy for similar concepts has applications in the education and machine
learning fields because they rely on word-sense disambiguation.

© Copyright IBM Corp. 2018, 2019 5-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Topics
• Natural language processing overview
• Natural language processing use cases
• Natural language processing basic concepts and terminology
• Natural language processing tools and services

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-13. Topics

© Copyright IBM Corp. 2018, 2019 5-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Basic concepts and terminologies

• Synonyms: Words that are written differently but are similar in
meaning.
ƒ Example: Clever and smart

• Antonyms: Words that have meanings that are opposite to each other.
ƒ Example: Clever and stupid

• Usage example: In information retrieval, you might want to expand the

keywords search by retrieving the synonyms of the query words.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-14. Basic concepts and terminologies

Synonyms are words that are written differently but are similar in meaning. For example:
• Clever and smart
• Begin and start
• Beautiful and pretty
• Sad and unhappy
Antonyms are words that have meanings that are opposite to each other. For example:
• Clever and stupid
• Begin and end
• Beautiful and ugly
• Sad and happy
Usage example: In information retrieval, you might want to expand the keywords search by
retrieving the synonyms of the query words.

© Copyright IBM Corp. 2018, 2019 5-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Basic concepts and terminologies (cont.)

Homonyms: Words that have the same written form but have unrelated
meanings. There are two types of homonyms:
• Homographs: Words that have the same written form. For example:
ƒ This answer is right.

ƒ The building is on the right side of the river.

ƒ You have the right to remain silent.

ƒ Come here right now.

• Homophones: Words that sound similar when spoken but have

different meanings and spellings. For example:
ƒ “left” and “lift”.

ƒ “right” and “write”.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-15. Basic concepts and terminologies (cont.)

Homonyms are words that have the same written form but have unrelated meanings. There are
two types of homonyms:
• Homographs
• Homophones
Homographs are words that have the same written form. For example:
• This answer is right.
• The building is on the right side of the river.
• You have the right to remain silent.
• Come here right now.
Although the word right has the same written form in the examples, you notice the difference
between the meanings in each sentence.
Homophones are words that sound similar when spoken but have different meanings and
spellings. For example:
• “left” and “lift”.
• “right” and “write”.

© Copyright IBM Corp. 2018, 2019 5-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Basic concepts and terminologies (cont.)

• Homonyms challenges:
ƒ How do you translate “right” so that it has the correct meaning?
ƒ How do you differentiate two words that sound similar when you
convert speech to text?

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-16. Basic concepts and terminologies (cont.)

Homonyms introduce challenges into NLP operations such as machine translation and speech
recognition. How do you translate right so that it has the correct meaning? How do you differentiate
two words that sound similar when you convert speech to text?

© Copyright IBM Corp. 2018, 2019 5-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Basic concepts and terminologies (cont.)

• Polysemy: Words that have the same written form and a related
meaning. For example:
ƒ You must face your fear.
ƒ Her face is beautiful.
• Hyponymy: A word is a hyponym of another word if it represents a
subclass of the other word. For example:
ƒ Orange is a hyponym of fruit.
ƒ Yellow is a hyponym of color.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-17. Basic concepts and terminologies (cont.)

Polysemy refers to words that have the same written form and related meaning. For example:
• You must face your fear.
• Her face is beautiful.
Hyponymy: A word is a hyponym of another word if it represents a subclass of the other word. For
example:
• Orange is a hyponym of fruit.
• Yellow is a hyponym of color.

© Copyright IBM Corp. 2018, 2019 5-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Basic concepts and terminologies (cont.)

• Hypernymy: One word is the hypernym of another word if it represents
a superclass of the other word. For example:
ƒ Fruit is a hypernym of orange.

ƒ Color is a hypernym of yellow.

• Usage example: Comparing the semantic similarity.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-18. Basic concepts and terminologies (cont.)

Hypernymy: One word is the hypernym of another word if it represents a superclass of the other
word. For example:
• Fruit is a hypernym of orange.
• Color is a hypernym of yellow.
Usage example: Comparing the semantic similarity.

© Copyright IBM Corp. 2018, 2019 5-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty
5.4. Natural language processing tools and
services

© Copyright IBM Corp. 2018, 2019 5-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing

tools and services

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-19. Natural language processing tools and services

© Copyright IBM Corp. 2018, 2019 5-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Topics
• Natural language processing overview
• Natural language processing use cases
• Natural language processing basic concepts and terminology
• Natural language processing tools and services

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-20. Topics

© Copyright IBM Corp. 2018, 2019 5-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing tools and services

Open-source NLP tools:
• Apache OpenNLP: Provides tokenizers, sentence segmentation, part-
of-speech tagging, named entity extraction, chunking, parsing, co-
reference resolution, and more.
• Stanford Core NLP: A suite of NLP tools that provide part-of-speech
tagging, a named entity recognizer, a co-reference resolution system,
sentiment analysis, and more.
• Natural Language Toolkit (NLTK): A Python library that provides
modules for processing text, classifying, tokenizing, stemming, tagging,
parsing, and more.
• WordNet: One of the most popular lexical databases for the English
language. Supported by various API and programming languages.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-21. Natural language processing tools and services

There are many open source tools that you can use for NLP. For example:
• Open NLP that is based on Java. It provides many functions for text processing, such as
tokenizers, sentence segmentation, part-of-speech tagging, named entity extraction, chunking,
parsing, co-reference resolution, and more. For more information, see
https://opennlp.apache.org/
• Stanford Core NLP, which is written in Java. It is a suite of NLP tools that provide part-of-speech
tagging, a named entity recognizer, a co-reference resolution system, sentiment analysis, and
more. It supports many languages, such as English, German, French, Arabic, Spanish, and
Chinese. For more information, see https://stanfordnlp.github.io/CoreNLP/.
• NLTK provides the same processes as the other NLP suites, but in the Python language. For
more information, see https://www.nltk.org/.
• WordNet is a popular lexical database that is used in research. There are many APIs and
languages that you can use to access WordNet. For example, you can make a call to retrieve a
synonym of a word. WordNet is available online and as an offline version that you can
download. For more information, see https://wordnet.princeton.edu/.

© Copyright IBM Corp. 2018, 2019 5-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty
There are other libraries, such as Unstructured Information Management Architecture (UIMA). IBM
Watson uses UIMA to analyze unstructured data. The Apache Clinical Text Analysis and
Knowledge Extraction System (Apache cTAKES) is a UIMA-based system that is used to extract
information from medical records.

© Copyright IBM Corp. 2018, 2019 5-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Natural language processing tools and services (cont.)

Services:
• Examples: IBM Cloud, Microsoft Cloud (Azure), and Google Cloud
• IBM offers its AI services through IBM Cloud. The NLP services that are
provided include the following ones (among others):
ƒ Watson Natural Language Classifier for text classification
ƒ Watson Natural Language Understanding for entity identification and
relation extraction

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-22. Natural language processing tools and services (cont.)

Instead of using low-level libraries, you can use many cloud services that accomplish high-level
NLP tasks, for example, IBM Cloud, Microsoft Cloud (Azure), and Google Cloud.
IBM offers its AI services through IBM Cloud. The NLP services that are provided include the
following ones (among others):
• Watson Natural Language Classifier for text classification
• Watson Natural Language Understanding for entity identification and relation extraction
You can rapidly build a complete NLP application by using these services.

© Copyright IBM Corp. 2018, 2019 5-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Unit summary
• Explain what natural language processing is.
• Identify NLP use cases.
• Explain basic NLP concepts and terminology.
• List the tools and services for NLP.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-23. Unit summary

© Copyright IBM Corp. 2018, 2019 5-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Review questions
1. Email spam detection is a use case of:
A. Sentiment analysis
B. Classification
C. Chatbots
D. Translation
2. “Apple" is the …… of “fruit"
A. Synonym
B. Antonym
C. Hypernymy
D. Hyponymy

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-24. Review questions

1. B. Classification.
2. D. Hyponymy.

© Copyright IBM Corp. 2018, 2019 5-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Review questions (cont.)

3. What are examples of information extraction?
A. Entities identification
B. Relation identification
C. Automatic summarization
D. All the above
4. “Ugly" is the …… of “pretty“.
A. Synonym
B. Antonym
C. Hypernymy
D. Hyponymy

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-25. Review questions (cont.)

3. D. All the above.

4. B. Antonym.

© Copyright IBM Corp. 2018, 2019 5-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Review answers
1. Email spam detection is a use case of:
A. Sentiment analysis
B. Classification
C. Chatbots
D. Translation
2. “Apple" is the …… of “fruit"
A. Synonym
B. Antonym
C. Hypernymy
D. Hyponymy

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-26. Review answers

1. Classification.
2. Hyponymy.

© Copyright IBM Corp. 2018, 2019 5-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 5. Introduction to natural language processing

Uempty

Review answers (cont.)

3. What are examples of information extraction?
A. Entities identification
B. Relation identification
C. Automatic summarization
D. All of the above
4. “Ugly" is the …… of “Pretty"
A. Synonym
B. Antonym.
C. Hypernymy
D. Hyponymy.

Introduction to natural language processing © Copyright IBM Corporation 2019

Figure 5-27. Review answers (cont.)

3. All the above.

4. Antonym.

© Copyright IBM Corp. 2018, 2019 5-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Unit 6. Natural language processing

concepts and components
Estimated time
00:30

Overview
This unit covers natural language processing components, the NLP pipeline, natural language
understanding, natural language generation, information retrieval, and information extraction.

© Copyright IBM Corp. 2018, 2019 6-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Unit objectives
• Define the NLP categories.
• Describe the NLP pipeline.
• Explain the challenges in natural language understanding (NLU).
• Explain the concepts of information retrieval and extraction.
• Describe sentiment analysis.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 6-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
6.1. Natural language processing categories

© Copyright IBM Corp. 2018, 2019 6-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing

categories

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-2. Natural language processing categories

© Copyright IBM Corp. 2018, 2019 6-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Topics
• Natural language processing categories
• Language ambiguities
• Natural language processing pipeline
• Information retrieval
• Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-3. Topics

© Copyright IBM Corp. 2018, 2019 6-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing categories

• Natural language understanding (NLU)
• Natural language generation (NLG)

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-4. Natural language processing categories

There are two categories of NLP:

• Natural language understanding (NLU): It is the NLP task of extracting insights from natural
language inputs.
• Natural language generation (NLG): it is the NLP task of building natural language outputs from
non-linguistic inputs.
Natural language exists in various media, such as text in documents, reports, or messages, or
speech.
The graphic in the slide shows that NLU is the NLP process that takes input text while NLG is the
NLP process that generates text as output.

© Copyright IBM Corp. 2018, 2019 6-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

NLU applications
• Unstructured to structured
• Question and answer system
• Sentiment analysis

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-5. NLU applications

NLU analyzes language to gain insights into the text. There many examples of NLU applications:
• Mapping a user’s unstructured input to a computer representation (structured data) and relation
extraction
• Question and answering system
• Sentiment analysis
The graphic in the slide shows an example of converting unstructured to structured data. The input
to the NLU system is natural language (unstructured text) and through the NLP process it is
converted to structured data (table).
References:
http://www.lacsc.org/papers/PaperA6.pdf
https://nlp.stanford.edu/~wcmac/papers/20140716-UNLU.pdf

© Copyright IBM Corp. 2018, 2019 6-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

NLG applications
• Machine translation
• Text summarization
• Weather forecasting system

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-6. NLG applications

Here are some NLG application examples:

• Translator.
• Text summarization.
• Weather Forecasting Systems, which compile graphical weather maps representations and
interpret the numbers that come from the prediction system. By using NLG, you can transform
this information into natural language.
References:
https://www.ibm.com/watson/services/language-translator/
http://www.academia.edu/3879518/Natural_Language_Generation_Scope_Applications_and_Appr
oaches

© Copyright IBM Corp. 2018, 2019 6-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
6.2. Language ambiguities

© Copyright IBM Corp. 2018, 2019 6-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Language ambiguities

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-7. Language ambiguities

© Copyright IBM Corp. 2018, 2019 6-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Topics
• Natural language processing categories
• Language ambiguities
• Natural language processing pipeline
• Information retrieval
• Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-8. Topics

© Copyright IBM Corp. 2018, 2019 6-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Language ambiguities

• Lexical ambiguity: A primitive level, such as at the word level

• Verb versus noun:
ƒ “We will dance all night.”
ƒ “This is the salsa dance.”
ƒ “John will go to work.”
ƒ “His uncle left him millions in his will.”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-9. Language ambiguities

Building applications with NLP processes is not a trivial task. Natural language includes many
ambiguities, such as a lexical ambiguity, which is a primitive level, such as at the word level.
Two examples:
• The word dance can be a verb (“We will dance all night.”) or a noun (“This is the salsa dance.”).
• The word will can be a helping verb to indicate an action in the future (“John will go to work”) or
a noun (“His uncle left him millions in his will.”).

© Copyright IBM Corp. 2018, 2019 6-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Language ambiguities (cont.)

• Syntactic-level ambiguity: A sentence that can be parsed in various

ways.
ƒ Example: “She pointed at the guy with the umbrella.”

• Anaphora ambiguity occurs when it is not clear which one is the

antecent noun that a pronoun replaces because more than one possible
antecendent exists.
ƒ Example: “When Mary invited Ann to play she did not know that she would
be late”.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-10. Language ambiguities (cont.)

Here are two more types of language ambiguity:

• Syntactic-level ambiguity: A sentence that can be parsed in various ways. For example: “She
pointed at the guy with the umbrella.” Did she use her umbrella to point at the guy or did she
point at the guy who is carrying an umbrella?
• Anaphora is an expression for which the interpretation depends on another expression that
was previously introduced. The referring term is called anaphor and it is usually a pronoun. The
pronoun takes the place of a noun but, to avoid ambiguity, the pronoun must refer clearly to the
noun that the pronoun replaces.
• An anaphora ambiguity occurs when more than one possible antecedent exists. For example:
“When Mary invited Ann to play she did not know that she would be late.” Is the first “she”
replacing Mary or Ann? Who did not know? Is the second “she” replacing Mary or Ann? Who
would be late?
References:
https://en.wikipedia.org/wiki/Syntactic_ambiguity
https://en.wikipedia.org/wiki/Anaphora_(linguistics)
http://www.ijircce.com/upload/2014/sacaim/59_Paper%2027.pdf

© Copyright IBM Corp. 2018, 2019 6-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
6.3. Natural language processing pipeline

© Copyright IBM Corp. 2018, 2019 6-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing

pipeline

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-11. Natural language processing pipeline

© Copyright IBM Corp. 2018, 2019 6-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Topics
• Natural language processing categories
• Language ambiguities
• Natural language processing pipeline
• Information retrieval
• Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-12. Topics

© Copyright IBM Corp. 2018, 2019 6-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline

• A pipeline is a way to design a program in which the output of one
module feeds into the input of the next module.
• Using the NLP pipeline divides the tasks of NLU, which makes NLU
less complicated.
• For example, use NLP pipeline to understand the following sentence:
“Yes, I received your invitation, and I will happily attend your party.”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-13. Natural language processing pipeline

When you work on an NLP task like machine translation, there are a set of processes and activities
that you must perform. This set of processes is the NLP pipeline.
A pipeline is a process for designing a program in which the output of one module feeds into the
input of the next module. You use the pipeline to break down the complexity of the NLP task into a
smaller set of less complicated tasks. There are no strict rules for the activities that must be done in
the pipeline.
In the following slides, we explore some of these activities by using the following example by
assuming the following statement:
“Yes, I received your invitation, and I will happily attend your party.”
This statement is understandable by a human but not a computer. We use the pipeline to walk
though each stage to analyze the statement.
Reference:
https://stanfordnlp.github.io/CoreNLP/pipelines.html

© Copyright IBM Corp. 2018, 2019 6-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

1. Sentence segmentation:
• Detect sentence boundaries.
• There are two sentences in the example that are separated by the
conjunction “and”:
ƒ “Yes, I received your invitation, and I will happily attend your party.”

• Apply this process to the example:

í “Yes, I received your invitation.”
í “I will happily attend your party.”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-14. Natural language processing pipeline (cont.)

Sentence segmentation focuses on finding the boundaries of sentences in text, that is, where the
sentence starts and ends. This is not an easy task to accomplish due to the possible ambiguity that
is caused by punctuation marks.
For example, a period might indicate the end of a sentence, but it might also indicate an
abbreviation, a decimal point, or an email address.
Assume that the two sentences here are separated by the conjunction “and”, so the result of this
stage is the following sentences:
• “Yes, I received your invitation.”
• “I will happily attend your party.”
Reference:
https://en.wikipedia.org/wiki/Sentence_boundary_disambiguation

© Copyright IBM Corp. 2018, 2019 6-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

2. Tokenization:
ƒ Breaks a sentence into tokens.
ƒ Tokenization uses delimiters, for example, a space ” “.
ƒ Apply tokenization to the example:
í First sentence: “Yes””,” “I” “received” “your” “invitation”
í Second sentence: “I” “will” “happily” “attend” “your” “party”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-15. Natural language processing pipeline (cont.)

Tokenization is a basic process that breaks a sentence into a group of words, punctuations,
numbers, and alphanumerics that are called tokens. The tokenization can be done on multiple
delimiters. Assume in the example that you use the white space as delimiter and apply tokenization
to the example:
First sentence: “Yes””,” “I” “received” “your” “invitation”
Second sentence: “I” “will” “happily” “attend” “your” “party”
White space is a standard delimiter, but is not sufficiently useful by itself. For example, segmenting
“New York” into “New” and “York” might introduce ambiguity because they both refer to a state, so
you should preserve the space in-between.
To read more about “the art of tokenization”, see the following website:
https://www.ibm.com/developerworks/community/blogs/nlp/entry/tokenization?lang=en

Note

Sentence segmentation, tokenization, and other activities in the pipeline might also differ depending
on the language. For example, you cannot use the same English tokenizer with the Japanese
language.

© Copyright IBM Corp. 2018, 2019 6-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

3. Parts of speech (POS) tagging:
• Tagging each token by what it corresponds to in a certain data set
(English grammar).
• POS helps the computer to understand language and grammar and
derive meaning from the input sentence.
• The most famous data sets is the Penn Treebank project.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-16. Natural language processing pipeline (cont.)

POS tagging: The process of tagging each token with its grammatical representation, such as
noun, verb, or adjective.
POS helps the computer to understand language and grammar and derive meaning from the input
sentence.
In the example, the data set is English grammar, so according to the POS that are defined, we want
to label each token by its proper grammar value, that is, the corresponding part of speech.
POS helps the computer to understand language and grammar and derive meaning from the input
sentence. Many human-annotated data sets are publicly available. One of the most famous data
sets is the one used by the Penn Treebank project.
References:
https://en.wikipedia.org/wiki/Part-of-speech_tagging
https://nlp.stanford.edu/software/tagger.shtml

© Copyright IBM Corp. 2018, 2019 6-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

Example of POS tagging

Tag Description

JJ Adjective

NN Noun Single

NNS Noun Plural

RB Adverb

RP Particle

VB Verb, base form

VBD Verb, past tense

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-17. Natural language processing pipeline (cont.)

Review the tags example to learn about tagging.

© Copyright IBM Corp. 2018, 2019 6-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

Applying NLP pipeline steps to the example:
• Example: “Yes, I received your invitation, and I will happily attend your
party.”
• The first sentence is: “yes””,” “I” “got” “your” “invitation”.
• The second sentence is: “I” “will” “happily” “attend” “your” “party”.
• Apply POS tags to both sentences.
ƒ First sentence: “yes/UH” “,/,” ”I/PRP” “got/VBD” “your/PRP$” “invitation/NN”
“,/,”
ƒ Second sentence: “I/PRP” “will/MD” “happily/RB” “attend/VB” “your/PRP$”
“party/NN”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-18. Natural language processing pipeline (cont.)

Example: “Yes, I received your invitation, and I will happily attend your party.”
1. Apply sentence segmentation:
▪ Sentence 1: Yes, I received your invitation.
▪ Sentence 2: I will happily attend your party.
2. Apply tokenization by using white space as delimiter:
▪ The first sentence is: “yes””,” “I” “got” “your” “invitation”.
▪ The second sentence is: “I” “will” “happily” “attend” “your” “party”.
3. Apply POS tagging:
▪ The output for the first sentence is: “yes/UH” “,/,” ”I/PRP” “got/VBD” “your/PRP$”
“invitation/NN” “,/,”
▪ The output for the second sentence is: “I/PRP” “will/MD” “happily/RB” “attend/VB”
“your/PRP$” “party/NN”

© Copyright IBM Corp. 2018, 2019 6-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

4. Morphological processing: Defines how morphemes are

constructed.
• For example, “happily” is broken into happy –ly.
• Word meanings change when you add or remove any affixes. For
example, certain and uncertain, or late and latest.
• Nouns can change to adjectives, for example, sadness to sad.
• Two words merge to form a new one, for example, “football”, divided
into two tokens “foot” and “ball”.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-19. Natural language processing pipeline (cont.)

Morphological parsing is the process of determining the morphemes of a word.

Morphemes represent the smallest grammatical units in a language and are not identical to a
word. The main difference between a morpheme and word is that a morpheme might or not stand
alone, and a word is freestanding.
Morphology focus on recognizing how base words were modified to form other words with similar
meanings but often with different syntactic categories.
In this step, you break strings of language into sets of tokens that correspond to discrete words. For
the example, a word token, such as “happily”, can be broken into two subword tokens as happy –ly.
This stage does not need to be performed in our example.
Word meanings change when you add or remove any affixes. For example, certain and uncertain,
or late and latest. Nouns can change to adjectives, for example, sadness to sad.
Morphology applies when two words merge to form a new one, for example, “football”, where it can
be divided into two tokens “foot” and “ball” to help understand the word meaning.
POS structures the tokens, morphology adjusts the meaning of each token. By changing the
language that is used, the rules also change.

© Copyright IBM Corp. 2018, 2019 6-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
References:
https://en.wikipedia.org/wiki/Morphological_parsing
https://en.wikipedia.org/wiki/Morpheme

© Copyright IBM Corp. 2018, 2019 6-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

5. Word-level (lexical) semantics:

• Deals with the meaning of words.
ƒ Example: “yes/UH” “,/,” ”I/PRP” “got/VBD” “your/PRP$” “invitation/NN” “,/,”.

• Can replace the “got” token with “received”.

ƒ Example: “yes/UH” “,/,” ”I/PRP” “received/VBD” “your/PRP$” “invitation/NN”
“,/,”.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-20. Natural language processing pipeline (cont.)

5) Word-level (lexical) semantic: Semantics deal with the meaning of words. In the example, we
have the following input for this stage:

1+1 2 Example

“yes/UH” “,/,” ”I/PRP” “got/VBD” “your/PRP$” “invitation/NN” “,/,”

The “got” token in the first sentence means “received”, so this token may be replaced with a more
appropriate token if necessary. So, the output would be:
“yes/UH” “,/,” ”I/PRP” “received/VBD” “your/PRP$” “invitation/NN” “,/,”

© Copyright IBM Corp. 2018, 2019 6-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

6. Parsing:
• Evaluate in terms of grammatical correctness.
• The input from the previous stage was:
ƒ First sentence: “yes/UH” “,/,” ”I/PRP” “received/VBD” “your/PRP$”
“invitation/NN” “,/,”

ƒ Second sentence: “I/PRP” “will/MD” “happily/RB” “attend/VB” “your/PRP$”

“party/NN”

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-21. Natural language processing pipeline (cont.)

Parsing or syntactic analysis is the process of evaluating text in terms of grammatical correctness
(if required).
The input from the previous stage was:
• First sentence: “yes/UH” “,/,” ”I/PRP” “received/VBD” “your/PRP$” “invitation/NN” “,/,”
• Second sentence: “I/PRP” “will/MD” “happily/RB” “attend/VB” “your/PRP$” “party/NN”
Reference:
https://hpi.de/fileadmin/user_upload/fachgebiete/plattner/teaching/NaturalLanguageProcessing/NL
P2016/NLP05_SyntacticParsing.pdf

© Copyright IBM Corp. 2018, 2019 6-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Natural language processing pipeline (cont.)

Parsing (cont.)

(ROOT (S (S (INTJ (UH yes)) (, ,) (NP (PRP I)) (VP (VBD got) (NP (PRP$
your) (NN invitation)))) (, ,) (CC and) (S (NP (PRP I)) (VP (MD will) (ADVP
(RB happily)) (VP (VB attend) (NP (PRP$ your) (NN party)))))))

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-22. Natural language processing pipeline (cont.)

One method for parsing is to group text into a tree structure. This technique is used in NLP tasks
like machine translations, grammar checker, speech recognition, and relation extraction.
Reference:
http://disi.unitn.it/moschitti/Teaching-slides/NLP-IR/NLP-Parsing.pdf

© Copyright IBM Corp. 2018, 2019 6-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
6.4. Information retrieval

© Copyright IBM Corp. 2018, 2019 6-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information retrieval

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-23. Information retrieval

© Copyright IBM Corp. 2018, 2019 6-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Topics
• Natural language processing categories
• Language ambiguities
• Natural language processing pipeline
• Information retrieval
• Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-24. Topics

© Copyright IBM Corp. 2018, 2019 6-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information retrieval

• Retrieve relevant information from a collection of information resources.

• Information retrieval is the foundation of many search engines.

• Upcoming tasks:
ƒ Stemming
ƒ Normalization
ƒ Term Frequency – Inverse Document Frequency (TF-IDF)

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-25. Information retrieval

The objective is to obtain relevant information from a collection of information resources.

Information retrieval is the foundation of many search engines.
Next, we will discuss a few tasks that are used in information retrieval:
• Stemming
• Normalization
• TF-IDF
Reference: https://nlp.stanford.edu/IR-book/html/htmledition/irbook.html

© Copyright IBM Corp. 2018, 2019 6-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Stemming
• Reduce a word to its word stem by removing its affixes.
• For example, the word “unbelievable” can be stemmed into “believ” by
removing the prefix “un” and the suffix “able”.
• The stem does not have to match the morphological root of the word.
For example, “Chance” stemmed to “Chanc”.
• The most popular English stemming algorithm is the Porter's algorithm
(Porter, 1980).

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-26. Stemming

Stemming is a task where algorithms reduce a word to its word stem by removing its affixes. For
example, the word “unbelievable” may be stemmed into “believ” by removing the prefix “un” and the
suffix “able”.
The stem does not have to match the morphological root of the word. Therefore, the stem form can
have no actual meaning, for example, the stem of the word "chance" is "chanc“, which is not an
English word on its own. The most popular English stemming algorithm is the Porter's algorithm
(Porter, 1980).

© Copyright IBM Corp. 2018, 2019 6-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Porter stemmer

Step Number Rule Example

sses → ss glasses → glass

ies → I parties → parti
1
ss → ss loss → loss
s→ø hats → hat

talking → talk
ing → ø
2 discovered → discover
ed → ø

ational → ate operational → operate

3 izer → ize recognizer → recognize
ator → ate collaborator → collaborate

al → ø
electrical → electric
able → ø
4 doable → do
ate → ø
investigate → investing

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-27. Porter stemmer

This table demonstrates some of the rules of the Porter stemmer.

© Copyright IBM Corp. 2018, 2019 6-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Normalization
• Used in many NLP problems, such as sentiment analysis and
information retrieval.
• Examples:
ƒ Case folding: Child Æ child
ƒ Duplication removal: Hiiiiii Æ Hi
ƒ Acronyms processing: WHO Æ World Health Organization
ƒ Format normalization: $100 Æ 100 dollars
ƒ Value normalization: 2 July 1980 Æ DATE

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-28. Normalization

Text normalization is the process of transforming text into a single form, which ensures consistency
before operations are performed on it.
For example, imagine that you have a dictionary that contains a set of words, and you also have
query text that includes one of the words in your dictionary. Assume that the word in the query is
Child with a capital letter C. But the equivalent word in the dictionary is child with a lowercase c
letter. Thus, both words do not match.
The solution is to ensure that the query text is “normalized” into lowercase and the set of words in
dictionary is also normalized into lowercase so that the query and dictionary have consistent text.
Here are some examples of normalization:
Examples:
• Case folding: Child → child
• Duplication removal: Hiiiiii → Hi
• Acronyms processing: WHO → World Health Organization
• Format normalization: $100 → 100 dollars
• Value normalization: 2 July 1980 → DATE

© Copyright IBM Corp. 2018, 2019 6-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
There are no strict rules for how normalization should be done. It depends on what type of text will
be normalized and how it will be processed later.

© Copyright IBM Corp. 2018, 2019 6-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Term Frequency – Inverse Document Frequency

• TF-IDF is a combination of two weighting methods for information
retrieval to determine how important a term is.
• TF: Term Frequency measures how many times a term t occurs in a
document d. This value is denoted by tft,d.
• IDF: Inverse Document Frequency measures how rare a term is. You
must decrease the frequent terms weight while increasing the weight of
the exceptional ones.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-29. Term Frequency – Inverse Document Frequency

The weighting methods in information retrieval determine how important a term is:
TF: Term Frequency measures how many times a term t occurs in a document d. This value is
denoted by tft,d .
IDF: Inverse Document Frequency measures how rare a term is.
Reference:
https://nlp.stanford.edu/IR-book/html/htmledition/tf-idf-weighting-1.html

© Copyright IBM Corp. 2018, 2019 6-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Term Frequency – Inverse Document Frequency (cont.)

• idf= log (Total number of documents (N) / Number of documents with
term t (dft))

• To generate a composite weight, term frequency and inverse document

frequency are multiplied as follows:

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-30. Term Frequency – Inverse Document Frequency (cont.)

While computing TF, all terms are considered equally important. However, certain terms, such as
"is", "of", and "that", usually appear in any document thus these terms are not actually important.
These non-important words are called stop words. Thus, we need to decrease the frequent terms
weight while increasing the weight of the exceptional ones. This is done through the idft equation
shown in the slide.

© Copyright IBM Corp. 2018, 2019 6-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty
6.5. Information extraction

© Copyright IBM Corp. 2018, 2019 6-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-31. Information extraction

© Copyright IBM Corp. 2018, 2019 6-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Topics
• Natural language processing categories
• Language ambiguities
• Natural language processing pipeline
• Information retrieval
• Information extraction

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-32. Topics

© Copyright IBM Corp. 2018, 2019 6-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information extraction
• Refers to the automatic extraction of structured information from
unstructured or semi-structured text.
• Examples of applications where information extraction is used:
ƒ Entities and relation identification
ƒ Sentiment analysis

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-33. Information extraction

Information extraction refers to the automatic extraction of structured information from unstructured
or semi-structured text.
For example, information extraction is used in the following applications:
• Entities and relation identification
• Sentiment analysis

© Copyright IBM Corp. 2018, 2019 6-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information extraction (cont.)

Entities and relation identification

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-34. Information extraction (cont.)

As shown in this slide, “Nobel Prize” and “Wilhelm Conrad Rontgen” are identified as entities. The
relationship is identified as awarded, which indicates the relationship between Wilhelm and the
Nobel Prize.

© Copyright IBM Corp. 2018, 2019 6-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Information extraction (cont.)

Sentiment analysis:
• Detects user’s opinions in text.
• Used in the field of chatbots, social media analysis, and others.
• Examples:
ƒ “Their service is amazing” is a positive sentiment.
ƒ “The quality of food in this restaurant is terrible” is a negative sentiment.
ƒ “I am going to school” is a neutral sentiment.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-35. Information extraction (cont.)

Sentiment analysis is the process of identifying emotions or opinions that are expressed in user
input. It is used heavily in the fields of chatbots and social media analysis. It is also used in
marketing because it captures a user’s opinion about a particular product or service so that an
organization can take corrective action to keep the user satisfied.
Examples:
• “Their service is amazing” is a positive sentiment.
• “The quality of food in this restaurant is terrible” is a negative sentiment.
• “I am going to school” is a neutral sentiment.

© Copyright IBM Corp. 2018, 2019 6-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Unit summary
• Define the NLP categories.
• Describe the NLP pipeline.
• Explain the challenges in natural language understanding (NLU).
• Explain the concepts of information retrieval and extraction.
• Describe sentiment analysis.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-36. Unit summary

© Copyright IBM Corp. 2018, 2019 6-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Review questions
1. The technique that is used to unify all date formats in your
data set into one common format is called:
a. Stemming
b. Tokenization
c. Normalization

2. What is the process of labeling tokens with their grammatical

label?
a. Tokenization
b. POS tagging
c. Lexical analysis
d. Parsing

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-37. Review questions

Normalization
1. POS tagging

© Copyright IBM Corp. 2018, 2019 6-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Review questions (cont.)

3. True or False: For any NLP task, you must apply every step
in the NLP pipeline.
4. True or False: Sentiment analysis is an NLU application.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-38. Review questions (cont.)

2. False
3. True

© Copyright IBM Corp. 2018, 2019 6-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Review answers
1. The technique that is used to unify all date formats in your
data set into one common format is called:
A. Stemming
B. Tokenization
C. Normalization
2. What is the process of labeling tokens with their grammatical
label?
A. Tokenization
B. POS tagging
C. Lexical analysis
D. Parsing

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-39. Review answers

1. Normalization
2. POS tagging

© Copyright IBM Corp. 2018, 2019 6-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 6. Natural language processing concepts and components

Uempty

Review answers (cont.)

3. True or False: For any NLP task, you must apply every step
in the NLP pipeline.
4. True or False: Sentiment analysis is an NLU application.

Natural language processing concepts and components © Copyright IBM Corporation 2019

Figure 6-40. Review answers (cont.)

3. False
4. True

© Copyright IBM Corp. 2018, 2019 6-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Unit 7. Natural language processing

evaluation metrics
Estimated time
00:30

Overview
This unit explains how to evaluate the quality of your natural language processing (NLP) algorithm.

© Copyright IBM Corp. 2018, 2019 7-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Unit objectives
• Define various metrics to measure the quality of NLP algorithms.
• Understand the difference between these metrics.

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 7-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation
• How can we measure the solution quality?
• Target: You developed a new search engine. You must define how well
it works.

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-2. System evaluation

How can we measure the solution quality? In this presentation, we focus on a basic metric to
evaluate system performance in information retrieval. Assume that you developed a search
algorithm that helps you to retrieve related words from a corpus that contains 1000 documents.
From these 1000 documents, assume 200 are relevant to the word cat, and the other 800
documents are irrelevant.

© Copyright IBM Corp. 2018, 2019 7-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

• You ran a search test for the word “cat”.
• After the test ran, the search engine retrieved the documents that are
shown here.

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-3. System evaluation (cont.)

You test your solution by searching for the word “cat”. Your algorithm returns 250 documents, where
150 documents are relevant (which means your algorithm missed 50 relevant documents) and 100
documents are irrelevant (which means your algorithm correctly eliminated 700 of the irrelevant
documents).

© Copyright IBM Corp. 2018, 2019 7-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

Confusion matrix

• How many relevant documents were retrieved by the algorithm?

150 documents Æ True positive (Tp).
• How many irrelevant documents were retrieved by the algorithm?
100 documents Æ False positive (Fp)
(total 250 documents retrieved – 150 relevant documents).
• How many relevant documents did the algorithm not retrieve?
50 documents Æ False negative (Fn).
• How many irrelevant documents did the algorithm not retrieve?
700 documents Æ True negative (Tn).
Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-4. System evaluation (cont.)

A confusion matrix, also known as an error matrix, is a specific table layout that enables
visualization of the performance of an algorithm.
Based on the results for this example, how many relevant documents were retrieved by the
algorithm? The answer is 150 documents. This value is the True positive (Tp).
Based on the results for this example, how many irrelevant documents were retrieved by the
algorithm? The answer is 100 documents (total 250 documents retrieved – 150 relevant
documents). This value is the False positive (Fp).
Based on the results for this example, how many relevant documents did the algorithm not
retrieve? The answer is 50 documents. This value is the False negative (Fn).
Based on the results for this example, how many irrelevant documents did the algorithm not
retrieve? The answer is 700 documents. This value is the True negative (Tn).
The objective is to improve the algorithm to decrease the Fp and Fn values.

© Copyright IBM Corp. 2018, 2019 7-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-5. System evaluation (cont.)

We map the confusion matrix to the graph to produce the visuals for Tp, Fp, Tn, and Fn. We add Tp
to the retrieved relevant documents area and Fp to the retrieved irrelevant area. We add Fn to the
not retrieved relevant area and Tn to the not retrieved irrelevant area.

© Copyright IBM Corp. 2018, 2019 7-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

Accuracy
• Calculates how many correct results your solution managed to identify.

Accuracy = (Tp+Tn)/(Tp+Tn+Fp+Fn)

• Apply the formula to the example.

Accuracy = (150+700)/(1000)

• Useful for symmetric data sets where the values of positive and
negatives are almost the same.

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-6. System evaluation (cont.)

Accuracy is as a numeric measure of how good your algorithm is. It calculates how many correct
results your solution managed to identify, which is the proportion of true results among the total
number of cases that are examined.
Accuracy is defined by the following formula, which includes the Tp, Tn, Fp, and Fn metrics:
Accuracy = (Tp+Tn)/(Tp+Tn+Fp+Fn)
By applying the values from the example, accuracy can be calculated as follows:
Accuracy = (150+700)/1000 = 0.85
Accuracy is a good measure but only when you have symmetric data sets where the number of
positive values and negatives values are almost the same. For example, if your data set is split as
90 positive samples and 10 negative samples, classifying all as positive gives a 0.90 accuracy
score.
Therefore, we must look at other metrics such as precision and recall to evaluate the quality of the
algorithm.

© Copyright IBM Corp. 2018, 2019 7-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

Precision
• Represents the fraction of retrieved documents that are relevant.

Precision = Tp/(Tp+Fp)

• Apply the formula to the example.

Precision = 150/(150+100)
Precision = 150/250 = 0.60

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-7. System evaluation (cont.)

Precision is a numeric measure that represents the fraction of retrieved documents that are
relevant. It is defined by the following formula:
Precision = Tp/(Tp+Fp)
Apply the formula to the example:
Precision = 150/(150+100)
150 retrieved relevant / 250 total retrieved = 0.60

© Copyright IBM Corp. 2018, 2019 7-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

Recall
• Represents the fraction of relevant documents that were retrieved.

Recall = Tp/(Tp+Fn)

• Apply the formula to the following example.

Recall = (150)/(150+50)
Recall = 150/200 = 0.75

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-8. System evaluation (cont.)

Recall is a numeric measure that represents the fraction of relevant documents that were retrieved.
It is defined by the following formula:
Recall = Tp/(Tp+Fn)
Apply the formula to the example:
Recall =150/(150+50)
150 retrieved relevant / 200 total relevant = 0.75

© Copyright IBM Corp. 2018, 2019 7-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

System evaluation (cont.)

F-Score (F-measure)
• Enables you to tradeoff precision against recall.
• The higher the F-score value is, the better the algorithm is.
• Here is the formula.

F = 2*Precision*Recall/(Precision+Recall)

• Apply the formula to the example.

F = (2*0.60*0.75)/(0.60+0.75)
F = 0.9/1.35= 0.6667

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-9. System evaluation (cont.)

The F-score (also called F-measure) is a measure that enables you to tradeoff precision against
recall by approximately averaging the precision and recall values.
The formula for F-score is:
F = (2*Precision*Recall)/(Precision +Recall)
Apply the formula to the example:
F = (2*0.60*0.75)/(0.60+0.75)
= 0.9/1.35= 0.6667

© Copyright IBM Corp. 2018, 2019 7-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Unit summary
• Define various metrics to measure the quality of NLP algorithms.
• Understand the difference between these metrics.

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-10. Unit summary

© Copyright IBM Corp. 2018, 2019 7-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Review questions
1. True or False: To calculate the F-score, you must calculate
accuracy first.
2. True or False: Accuracy is the harmonic mean of precision
and recall.
3. Assume that you developed an algorithm and calculated the
Precision as 0.5 and the Recall as 0.5, what is the value of
F-score in this case?
a. 0.25
b. 1.00
c. 0.50

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-11. Review questions

1. False
2. False
3. C: 0.50

© Copyright IBM Corp. 2018, 2019 7-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Review questions (cont.)

4. The F-score is calculated as (hint P=precision, R= Recall):

a. 2*(P+R)/(P+R)
b. 2*(P*R)/(P+R)
c. (P*R)/2*(P+R)
d. (P+R)/2*(P*R)

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-12. Review questions (cont.)

4. B: 2*(P*R)/(P+R)

© Copyright IBM Corp. 2018, 2019 7-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Review answers
1. True or False: To calculate the F-score, you must calculate
accuracy first.
2. True or False: Accuracy is the harmonic mean of precision
and recall.
3. Assume that you developed an algorithm and calculated the
Precision as 0.5 and the Recall as 0.5. What is the value of
F-score in this case?
A. 0.25
B. 1.00
C. 0.50

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-13. Review answers

1. False
2. False
3. C: 0.50

© Copyright IBM Corp. 2018, 2019 7-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 7. Natural language processing evaluation metrics

Uempty

Review answers (cont.)

4. F-score is calculated as (hint P=precision, R= Recall):

A. 2*(P+R)/(P+R)
B. 2*(P*R)/(P+R)
C. (P*R)/2*(P+R)
D. (P+R)/2*(P*R)

Natural language processing evaluation metrics © Copyright IBM Corporation 2019

Figure 7-14. Review answers (cont.)

4. B: 2*(P*R)/(P+R)

© Copyright IBM Corp. 2018, 2019 7-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Unit 8. Natural language processing

and IBM Watson
Estimated time
00:30

Overview
This unit lists the Watson services and software that are based on natural language processing
(NLP) and explains the main capabilities of IBM Watson Natural Language Classifier, IBM Watson
Natural Language Understanding, and IBM Watson Discovery.

© Copyright IBM Corp. 2018, 2019 8-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Unit objectives
• List the NLP Watson services.
• List the Watson services that perform information extraction.
• Describe the capabilities of IBM Watson Natural Language Classifier.
• Describe the capabilities of the IBM Watson Natural Language
Understanding.
• Describe the capabilities of IBM Watson Discovery.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 8-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
8.1. Watson NLP services

© Copyright IBM Corp. 2018, 2019 8-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson NLP services

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-2. Watson NLP services

© Copyright IBM Corp. 2018, 2019 8-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Topics
• Watson NLP services
• Watson Natural Language Classifier
• Watson Natural Language Understanding
• Watson Discovery

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-3. Topics

© Copyright IBM Corp. 2018, 2019 8-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson NLP services

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-4. Watson NLP services

Many Watson services have NLP at their core. The slide shows all the Watson NLP services on
IBM Cloud and IBM Watson Explorer which is an NLP application but it is not available on IBM
Cloud. For more information about IBM Watson Explorer, see
https://www.ibm.com/products/watson-explorer.
The remainder of this presentation focuses on three Watson NLP services:
• Watson Natural Language Classifier
• Watson Natural Language Understanding
• Watson Discovery
Other presentations in this course cover Watson Assistant and Watson Knowledge Studio in detail.

© Copyright IBM Corp. 2018, 2019 8-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Information extraction by using Watson services

• Watson NLP services that extract information from unstructured text:
ƒ Watson Natural Language Understanding
ƒ Watson Discovery
ƒ Watson Tone Analyzer
ƒ Watson Personality Insights

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-5. Information extraction by using Watson services

The Watson Natural Language Understanding, Watson Discovery, Watson Tone Analyzer, and
Watson Personality Insights services are based on natural language processing (NLP) technology
to extract information from unstructured text.
Unlike Watson Natural Language Classifier, these services can be used without training by the user
because they include a built-in public model, which means they are pre-trained on a public training
data set and ready to use immediately. However, to improve the accuracy of the service for a given
domain, NLU and Discovery should also be trained.

© Copyright IBM Corp. 2018, 2019 8-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
8.2. Watson Natural Language Classifier

© Copyright IBM Corp. 2018, 2019 8-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language

Classifier

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-6. Watson Natural Language Classifier

© Copyright IBM Corp. 2018, 2019 8-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Topics
• Watson NLP services
• Watson Natural Language Classifier
• Watson Natural Language Understanding
• Watson Discovery

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-7. Topics

© Copyright IBM Corp. 2018, 2019 8-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Classifier

• Classify natural language phrases into categories or classes.

• The following graphic shows the Watson NLC process.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-8. Watson Natural Language Classifier

Watson Natural Language Classifier is a service on IBM Cloud. It mimics the human ability to
classify naturally expressed phrases into categories or classes.
Watson NLC applies deep learning techniques to make predictions about the best predefined
classes for short sentences or phrases. It helps your application understand the language of short
texts and make predictions about how to handle them. It is useful for many use cases, for example,
it can be used in banking and finance to classify investments, risks, and transactions.
The Watson NLC process has four main phases:
• Training data preparation: You identify classes labels and collect the representative text
sample for each label.
• Create and train the classifier: Upload the training data to initiate training.
• Query the trained classifier: Test the classifier by sending text to classify.
• Evaluate and update the training data: Based on the test result, update the training data and
train your classifier as needed.
A classifier learns from your example data and then can return information for texts on which it is
not trained.

© Copyright IBM Corp. 2018, 2019 8-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
Reference:
https://console.bluemix.net/docs/services/natural-language-classifier/natural-language-classifier-ov
erview.html#about

© Copyright IBM Corp. 2018, 2019 8-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Classifier (cont.)

Training the comma-separated value data format

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-9. Watson Natural Language Classifier (cont.)

The data that is used to train the Watson NLC is in comma-separated value (CSV) format. In the
CSV format, a row in the file represents an example record. Each record has two or more columns:
• The first column is for sample input text that is used for training
• The second column is the category or label that matches the text.
As shown in the training set, multiple variations for each label were inserted. The more examples
and variations that are added, the better the results that you can expect from the classifier.
Reference:
https://console.bluemix.net/docs/services/natural-language-classifier/using-your-data.html#data-pr
eparation

© Copyright IBM Corp. 2018, 2019 8-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Classifier (cont.)

• Example: Is it hot outside?
• The Watson NLC instance was trained on only two categories:
temperature and conditions.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-10. Watson Natural Language Classifier (cont.)

In the online Watson NLC demonstration, the Watson NLC service instance that was used was
trained on only two categories: temperature and conditions. Therefore, based on the information
that is entered by the user, the output is the category (temperature or conditions) and confidence
score.
Notice in the output category temperature and confidence 100% were returned for our first input.
(“Is it hot outside?”). Because this question was used for training, the classifier knows with certainty
that it belongs to the temperature category.
Reference:
https://natural-language-classifier-demo.ng.bluemix.net/

© Copyright IBM Corp. 2018, 2019 8-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Classifier (cont.)

• The confidence level can change.
• Example: Will it be foggy outside? Watson NLC classification
(conditions) and confidence score (95%).

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-11. Watson Natural Language Classifier (cont.)

When the sentence changes, the confidence varies depending on how similar the question is to the
training data set.

© Copyright IBM Corp. 2018, 2019 8-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
8.3. Watson Natural Language Understanding

© Copyright IBM Corp. 2018, 2019 8-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language

Understanding

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-12. Watson Natural Language Understanding

© Copyright IBM Corp. 2018, 2019 8-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Topics
Watson NLP services
Watson Natural Language Classifier
Watson Natural Language Understanding
Watson Discovery

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-13. Topics

© Copyright IBM Corp. 2018, 2019 8-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding

• NLU extracts meaning from unstructured data.
• NLU processes input provided as text, HTML, or a public URL.
• NLU analyzes the input text and provides an output that includes:
ƒ Entities and relationships
ƒ Sentiment analysis
ƒ Keywords
• It can be trained by creating a custom model by using IBM Watson
Knowledge Studio.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-14. Watson Natural Language Understanding

Watson Natural Language Understanding (NLU) includes a set of text analytics features that you
can use to extract meaning from unstructured data. NLU accepts user input and provides an output
that includes entities and relationships that are found within the text and performs sentiment
analysis of the input text.
Input can be in the form of text, raw HTML, or a public URL. The service cleans HTML content
before analysis by default so the results can ignore most advertisements and other unwanted
content.
You can create custom models by using Watson Knowledge Studio to detect custom entities and
relations in NLU.
Reference:
https://console.bluemix.net/apidocs/natural-language-understanding#introduction

© Copyright IBM Corp. 2018, 2019 8-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

• Here is an example that uses the “Africa” article from Wikipedia.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-15. Watson Natural Language Understanding (cont.)

Using the Watson Natural Language Understanding service, we examine the “Africa” article from
Wikipedia. We use the online demonstration to analyze and display the results.

© Copyright IBM Corp. 2018, 2019 8-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-16. Watson Natural Language Understanding (cont.)

Choose different tabs to view the results:

• The Sentiment tab analyzes the general sentiment of the content or the sentiment toward
specific target phrases.
• The Emotion tab detects anger, disgust, fear, joy, or sadness that is conveyed in the content or
by the context around target phrases that are specified in the targets parameter.

© Copyright IBM Corp. 2018, 2019 8-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-17. Watson Natural Language Understanding (cont.)

The Keywords tab returns important keywords in the content.

© Copyright IBM Corp. 2018, 2019 8-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-18. Watson Natural Language Understanding (cont.)

The Entities tab identifies people, locations, organizations, and other subjects.

© Copyright IBM Corp. 2018, 2019 8-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-19. Watson Natural Language Understanding (cont.)

The Categories tab classifies and categorizes the content into a five-level taxonomy.

© Copyright IBM Corp. 2018, 2019 8-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-20. Watson Natural Language Understanding (cont.)

The Concepts tab recognizes high-level concepts that are related to the text. For example, the
analysis of a research paper about deep learning would likely return the concept "Artificial
Intelligence”, even if that term is not explicitly mentioned in the paper.

© Copyright IBM Corp. 2018, 2019 8-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Natural Language Understanding (cont.)

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-21. Watson Natural Language Understanding (cont.)

The Semantic Roles tab parses sentences into subject, action, and object form.

© Copyright IBM Corp. 2018, 2019 8-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
8.4. Watson Discovery

© Copyright IBM Corp. 2018, 2019 8-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Discovery

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-22. Watson Discovery

© Copyright IBM Corp. 2018, 2019 8-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Topics
• Watson NLP services
• Watson Natural Language Classifier
• Watson Natural Language Understanding
• Watson Discovery

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-23. Topics

© Copyright IBM Corp. 2018, 2019 8-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Discovery
• Adds cognitive search and content analytics to applications to identify
patterns, trends, and insights.
• Unlocks actionable insights into unstructured data.
• Unifies structured and unstructured data.
• Uses simple query language to eliminate the need for manual filtering of
results.
• Parses documents and enables the user to search through the
documents by using a natural language query.
• Can be trained.
• Includes the Discovery API and Discovery tooling.
• Example application: Find answers to FAQs

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-24. Watson Discovery

Watson Discovery
Watson Discovery is a cognitive search and content analytics engine that enables you to add a
cognitive search and content analytics engine to applications to identify patterns, trends, and
actionable insights that drive better decision-making. You can rapidly build cognitive, cloud-based
exploration applications that unlock actionable insights that are hidden in unstructured data.
You can securely unify structured and unstructured data with pre-enriched content, and use a
simplified query language to eliminate the need for manual filtering of results.
With Discovery, you can prepare your unstructured data, create a query that will pinpoint the
information you need, and then integrate those insights into your new application or existing
solution.

© Copyright IBM Corp. 2018, 2019 8-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
The Discovery services includes:
• Discovery API: The Discovery service supports a number of SDKs to simplify the development
of applications. The SDKs are available for many popular programming languages and
platforms, including Node.js, Java, and Python.
• Discovery tooling: The Discovery service includes a complete set of online tools - the Discovery
tooling - to help you quickly setup an instance of the service and populate it with data. The
Discovery service tooling has been designed to save time by eliminating the need to use APIs
to configure and populate your service.
With Discovery, you can build applications that extract the correct answers to FAQs by enriching
and searching data collections.

© Copyright IBM Corp. 2018, 2019 8-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Discovery flow
• Discovery provides an end-to-end solution that includes document
conversion, data storage, and a simplified query language.
• Discovery uses enrichments provided by the Natural Language
Understanding service

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-25. Discovery flow

The slide shows the architecture of a complete Discovery service solution:

Data
Accepts the following document formats:
• .pdf
• .docx
• HTML
• JSON
Ingestion
Documents are automatically converted and enriched by using the Watson APIs to add NLP
metadata to the content making it easier to explore and discover insights.
Storage
Data is indexed into a collection as part of your environment in the cloud.
Query
Understand data faster, create better hypothesis and deliver better outcomes.

© Copyright IBM Corp. 2018, 2019 8-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
Output
Actionable insights.
Comparing Watson NLU to Watson Discovery, notice that Watson Discovery is an end-to-end
solution that includes document conversion, data storage, and a simplified query language.
Watson Discovery use enrichments that are powered by the Watson Natural Language
Understanding service, that is, NLU is built into Watson Discovery.

© Copyright IBM Corp. 2018, 2019 8-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Discovery News

• Data collection of recent news articles.
• It is pre-enriched with the following cognitive metadata:
ƒ Keyword Extraction, Entity Extraction, Semantic Role Extraction, Sentiment
Analysis, Relation Extraction, and Category Classification

• Supports English, Spanish, German, Korean, and Japanese.

• Updated continuously with new articles.
• Use cases
ƒ News alerting
ƒ Event detection
ƒ Trending topics in news

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-26. Watson Discovery News

Discovery News is a public data set that has been pre-enriched with cognitive insights. It is also
included with Discovery. You can use this public, unstructured data set to query for insights that you
can integrate into your applications.
Watson Discovery News is an indexed dataset that is pre-enriched with the following cognitive
insights:
• Keyword extraction
• Entity extraction
• Semantic role extraction
• Sentiment analysis
• Relation extraction
• Category classification

© Copyright IBM Corp. 2018, 2019 8-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty
Watson Discovery News is updated continuously with new articles, and is available in English,
Spanish, German, Korean, and Japanese.
• Discovery News English is updated with approximately 300,000 new articles daily.
• Discovery News Spanish is updated with approximately 60,000 new articles daily.
• Discovery News German is updated with approximately 40,000 new articles daily.
• Discovery News Korean is updated with 10,000 new articles daily.
• Discovery News Japanese is updated with approximately 17,000 new articles daily.
The news sources vary by language, so the query results for each collection will not be identical.
Use cases for Watson Discovery News:
• News alerting - Create news alerts by taking advantage of the support for entities, keywords,
categories, and sentiment analysis to watch for both news and how it is perceived.
• Event detection - The subject/action/object semantic role extraction checks for terms/actions
such as "acquisition", "election results", or "IPO".
• Trending topics in the news - Identify popular topics and monitor increases and decreases in
how frequently they (or related topics) are mentioned.
Reference:
https://www.ibm.com/blogs/bluemix/2017/08/watson-discovery-service-updates-news-nlp/

© Copyright IBM Corp. 2018, 2019 8-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Watson Discovery News service

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-27. Watson Discovery News service

Access the Watson Discovery News demonstration to quickly find insights in the Watson Discovery
News data collection of recent news articles. Easily explore a company's:
• Top stories over the last two months
• Top entities (people, topics, companies) mentioned in those articles
• Trend of public sentiment in news
• Anomalous periods of high press coverage
• Trend of most commonly paired entities (co-mentions)
You can access the demonstration at https://discovery-news-demo.ng.bluemix.net/.

© Copyright IBM Corp. 2018, 2019 8-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Unit summary
• List the NLP Watson services.
• List the Watson services that perform information extraction.
• Describe the capabilities of IBM Watson Natural Language Classifier.
• Describe the capabilities of the IBM Watson Natural Language
Understanding.
• Describe the capabilities of IBM Watson Discovery.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-28. Unit summary

© Copyright IBM Corp. 2018, 2019 8-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Review questions
1. Which of the following inputs can be analyzed by Watson
Natural Language Understanding?
A. Text.
B. HTML.
C. Public URL.
D. All the above.
2. True or False: Watson Discovery News is updated
continuously with new articles.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-29. Review questions

1. D.
2. True.

© Copyright IBM Corp. 2018, 2019 8-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Review questions (cont.)

3. Watson Discovery provides one of the following capabilities:
A. Returns best matching class for a sentence or phrase.
B. Identifies a variety of tones at both the sentence and
document level.
C. Derives insights from transactional and social media data to
identify psychological traits.
D. Adds cognitive search and content analytics to applications to
identify patterns, trends, and insights.

4. True or False: Discovery provides an end-to-end solution

that includes document conversion, data storage, and a
simplified query language.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-30. Review questions (cont.)

3. D (A is Natural Language Classifier, B is Tone Analyzer, and C is Personality Insights).

4. True.

© Copyright IBM Corp. 2018, 2019 8-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Review answers
1. Which of the following inputs can be analyzed by Watson
Natural Language Understandingt?
A. Text.
B. HTML.
C. Public URL.
D. All of the above.

2. True or False: Watson Discovery News is updated

continuously with new articles.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-31. Review answers

1. D
2. True.

© Copyright IBM Corp. 2018, 2019 8-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Review answers (cont.)

3. Watson Discovery provides one of the following capabilities:
A. Returns best matching class for a sentence or phrase.
B. Identifies a variety of tones at both the sentence and
document level.
C. Derives insights from transactional and social media data to
identify psychological traits.
D. Adds cognitive search and content analytics to applications to
identify patterns, trends, and insights.

4. True or False: Discovery provides an end-to-end solution

that includes document conversion, data storage, and a
simplified query language.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-32. Review answers (cont.)

3. D (A is Natural Language Classifier, B is Tone Analyzer, and C is Personality Insights).

4. True.

© Copyright IBM Corp. 2018, 2019 8-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Exercise: Ingest, convert,

enrich, and query with Watson
Discovery service

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-33. Exercise: Ingest, convert, enrich, and query with Watson Discovery service

© Copyright IBM Corp. 2018, 2019 8-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 8. Natural language processing and IBM Watson

Uempty

Exercise objectives
• With Watson Discovery, it only takes a few steps to prepare
your unstructured data, create a query that will pinpoint the
information you need, and then integrate those insights into
your new application or existing solution.
ƒ This exercise takes you through the process of preparing and
querying a collection of documents.

• After completing this exercise, you should be able to:

ƒ Create a Watson Discovery service instance.
ƒ Create a collection.
ƒ Add content to a collection.
ƒ Create a custom configuration.
ƒ Build queries.
ƒ Use the Watson Discovery API.

Natural language processing and IBM Watson © Copyright IBM Corporation 2019

Figure 8-34. Exercise objectives

After completing this exercise, you should be able to:

• Create a Watson Discovery service instance.
• Create a collection.
• Add content to a collection.
• Create a custom configuration.
• Build queries.
• Use the Watson Discovery API.

© Copyright IBM Corp. 2018, 2019 8-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Unit 9. Introduction to IBM Watson

Knowledge Studio
Estimated time
00:45

Overview
This unit introduces IBM Watson Knowledge Studio, its capabilities, and features. This unit explains
the end-to-end domain adaptation process.

© Copyright IBM Corp. 2018, 2019 9-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Unit objectives
•Describe IBM Watson Knowledge Studio.
•List the Watson services that are trained by Knowledge Studio.
•List the Knowledge Studio workspace resources.
•Explain the process to build Knowledge Studio models that can be
deployed and used with other Watson services.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 9-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
9.1. IBM Watson Knowledge Studio overview

© Copyright IBM Corp. 2018, 2019 9-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

IBM Watson Knowledge

Studio overview

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-2. IBM Watson Knowledge Studio overview

© Copyright IBM Corp. 2018, 2019 9-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Topics
• IBM Watson Knowledge Studio overview
• Watson Knowledge Studio features
• Adapting the system to a new domain

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-3. Topics

© Copyright IBM Corp. 2018, 2019 9-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

What is Watson Knowledge Studio

• Use Knowledge Studio to create:
ƒ A machine learning model that understands the linguistic nuances,
meaning, and relationships that are specific to your industry.
ƒ A rule-based model that finds entities in documents.
• The model that you create with Knowledge Studio is a software
component that can be plugged into a natural language processing
(NLP) pipeline.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-4. What is Watson Knowledge Studio

Knowledge Studio is a service on IBM Cloud that can help you create a machine learning model
that understands the linguistic nuances, meaning, and relationships that are specific to your
domain. It also can help you create a rule-based model that finds entities in documents that is
based on rules that you define.
• Machine learning model: Uses a statistical approach to find entities and relationships in
documents. This type of model can adapt as the amount of data grows.
• Rule-based model: Uses a declarative approach to finding entities in documents. This type of
model is more predictable, and is easier to comprehend and maintain. However, it does not
learn from new data. It can find only patterns that it has been trained to find.
The model that you create with Knowledge Studio is a software component that can be plugged into
a natural language processing (NLP) pipeline.
References:
https://console.bluemix.net/docs/services/knowledge-studio/index.html#wks_overview_full
https://www.youtube.com/watch?v=r2xYHW0iyZM&index=3&list=PLZDyxLlNKRY9yM_Deg6GhTU
1WS0-JLwyX&
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS6

© Copyright IBM Corp. 2018, 2019 9-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

What is Watson Knowledge Studio (cont.)

• Easy-to-use tools for annotating unstructured domain literature.
• Uses those annotations to create a custom machine learning model.
• The accuracy of the model improves through iterative testing.
• Deploy the finished model to find and extract mentions of relationships and entities.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-5. What is Watson Knowledge Studio (cont.)

Knowledge Studio provides easy-to-use tools for annotating unstructured domain literature, and
uses those annotations to create a custom machine learning model that understands the language
of the domain. The accuracy of the model improves through iterative testing, ultimately resulting in
an algorithm that can learn from the patterns that it sees and recognizes those patterns in large
collections of new documents.
You can deploy the finished machine learning model to other Watson cloud-based offerings and
cognitive solutions to find and extract mentions of relationships and entities, including entity
coreferences.
References:
https://console.bluemix.net/docs/services/knowledge-studio/index.html#wks_overview_full
https://www.youtube.com/watch?v=r2xYHW0iyZM&index=3&list=PLZDyxLlNKRY9yM_Deg6GhTU
1WS0-JLwyX&

© Copyright IBM Corp. 2018, 2019 9-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Building a machine learning model

1. Import domain-specific documents.
2. Human annotators annotate documents.
3. Knowledge Studio uses a ground truth to train a model.
4. A trained model is ready to find entities, relationships, and co-
references in new documents.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-6. Building a machine learning model

1. Based on a set of domain-specific source documents, the team creates a type system that
defines entity types and relation types for the information of interest to the application that uses
the model.
2. A group of two or more human annotators annotates a small set of source documents to label
words that represent entity types, identify relationship types where the text identifies
relationships between entity mentions, and define co-references, which identify different
mentions that refer to the same thing, that is, the same entity. Any inconsistencies in the
annotations are resolved, and one set of optimally annotated documents is built, which forms
the ground truth.
3. Knowledge Studio uses the ground truth to train a model.
4. The trained model is used to find entities, relationships, and co-references in new documents.
References:
https://console.bluemix.net/docs/services/knowledge-studio/index.html#wks_overview_full
https://www.youtube.com/watch?v=r2xYHW0iyZM&index=3&list=PLZDyxLlNKRY9yM_Deg6GhTU
1WS0-JLwyX&

© Copyright IBM Corp. 2018, 2019 9-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Building a rule-based model

• A rule-based model can recognize patterns in your documents.
• Create rules to capture patterns in documents and convey information
about underlying entity types.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-7. Building a rule-based model

Create a rule-based model that can recognize patterns in your documents. Use rules to capture
patterns that occur in documents and convey information about underlying entity types. Rules can
be defined to recognize person’s names, money, dates, percentage, and more.

© Copyright IBM Corp. 2018, 2019 9-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Building a rule-based model (cont.)

• Tools to define rules:
ƒ Dictionary
ƒ Regular expression tool (Regex tool)
• Use the rule-based model to do useful things like pre-annotating
documents to speed up the human annotation process for a machine
learning model.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-8. Building a rule-based model (cont.)

Knowledge Studio provides a rule editor that simplifies the process of finding and capturing
common patterns in your documents as rules. It uses dictionaries to speed up the annotation
process.
The rule editor provides some tools that help you define rules:
• Dictionary: Add a dictionary and assign it a class name. Any words that are found that match
entries in the dictionary are automatically annotated with the dictionary class.
• Regular expression: A regular expression is a sequence of characters that define a search
pattern. The Regex tool that is included in the rule editor recognizes expressions. For example,
your documents might have several references like the following ones:
▪ 35-year-old driver
▪ 16-year-old learner
The syntax n-year-old x is a pattern that typically represents a person. You can define a regular
expression rule to find phrases that match the n-year-old x pattern, and annotate them as
PERSON entity mentions.

© Copyright IBM Corp. 2018, 2019 9-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
References:
https://console.bluemix.net/docs/services/knowledge-studio/index.html#wks_overview_full
https://developer.ibm.com/tv/accelerate-watson-model-development-rule-based-approach/

© Copyright IBM Corp. 2018, 2019 9-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Machine learning based model versus a rule-based model

Model type Pros Cons

Machine • Statistical (teaches by example). • Requires work to develop a supervised

learning • Useful for complex text extraction that has corpora (ground truth), and it requires
based many variations. certain amount of data.
• Scalable. • Sometime trapped by corner cases.

Rule based • Declarative (codify a set of rules). • Requires work to develop, write, and
• Useful for basic text extraction, for define a set of rules.
example, extracting emails, URLs, and • As complexity grows, maintenance
phone numbers. becomes an issue.
• Easy to comprehend and maintain.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-9. Machine learning based model versus a rule-based model

Machine learning models learn by examples that contain the information that we want to extract for
the specific domain. A machine learning model is useful when the information that you are
interested in does not have a certain form that can be codified into a rule, which is the case with
unstructured natural language.
Rule-based models are most useful when they are used to extract data that is known to have a
certain format, such as email addresses or phone numbers. If the information has many forms that
it can come in, then you must define a rule or set of rules for each format, which is inefficient if the
information that you must extract comes in many forms and has many variations.
The table summarizes both model types and their pros and cons.
Reference:
https://developer.ibm.com/tv/accelerate-watson-model-development-rule-based-approach/

© Copyright IBM Corp. 2018, 2019 9-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Why do we need Watson Knowledge Studio

• With Knowledge Studio, you can create, evaluate, and improve models
for new domains.
• A model adds annotations (metadata) to text that appears in natural
language content.
• The annotations, identify mentions of entities of interest in your domain
content, the relationships between them, and how the mentions co-
reference the same entity.
• Applications can use the annotations to automatically analyze and
process text.
• Application users benefit from this level of analysis by extracting
meaning, discovering insights, and obtaining answers in a natural
language context.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-10. Why do we need Watson Knowledge Studio

With Knowledge Studio, you can create, evaluate, and improve models for new domains. A model
adds annotations (metadata) to text that appears in natural language content. The annotations,
which identify mentions of entities of interest in your domain content, the relationships between
them, and how the mentions co-reference the same entity, can be used by applications to
automatically analyze and process text. Application users benefit from this level of analysis by
being able to extract meaning, discover insights, and obtain answers in a natural language context.

© Copyright IBM Corp. 2018, 2019 9-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Why do we need Watson Knowledge Studio (cont.)

• Teach by example: Empower domain

subject matter experts to teach Watson the
language of your domain without requiring
deep technical skills or coding.
• Engage your experts: Bring your experts
together in a collaborative online
environment to teach Watson.
• Use everywhere: Apply your models to
Watson Discovery, Watson Natural
Language Understanding, and Watson
Explorer.
• Knowledge Studio is end-to-end:
Combines annotation, training, and
evaluation in a single collaboration-focused
service.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-11. Why do we need Watson Knowledge Studio (cont.)

To become a subject matter expert in an industry or domain, Watson services must be trained to
understand specialized terminology and the relationships between entities. Knowledge Studio
facilitates the training of some Watson offerings. Knowledge Studio simplifies the task of building
machine learning models by helping subject matter experts to train Watson based on examples
without code.
Knowledge Studio allows you to:
• Teach by example: Empower domain subject matter experts to teach Watson the language of
your domain without requiring deep technical skills or coding.
• Engage your experts: Bring your experts together in a collaborative online environment to
teach Watson how to understand the linguistic nuances of your domain.
• Use everywhere: Apply what you taught Watson in multiple applications by using models from
Knowledge Studio in Discovery, Natural Language Understanding, and Explorer.
• Knowledge Studio is end-to-end: It is the only offering in the market that combines the
powerful capabilities of annotation, training, and evaluation in a single collaboration-focused
service.

© Copyright IBM Corp. 2018, 2019 9-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
9.2. Watson Knowledge Studio features

© Copyright IBM Corp. 2018, 2019 9-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Watson Knowledge Studio

features

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-12. Watson Knowledge Studio features

© Copyright IBM Corp. 2018, 2019 9-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Topics
• IBM Watson Knowledge Studio overview
• Watson Knowledge Studio features
• Adapting the system to a new domain

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-13. Topics

© Copyright IBM Corp. 2018, 2019 9-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Creating a workspace
• Create single workspace for each model.
• The workspace contains the artifacts and resources needed to build the
model.
• One workspace may contain one rule-based model and one machine
learning model.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-14. Creating a workspace

The first step in building a custom model is to create a workspace. For each model that you want to
build and use, create a single workspace that contains the artifacts and resources that are needed
to build the model. You can create one workspace that contains both one rule-based model and one
machine learning model. Then, you train the model to produce a custom model that can be
deployed to an external service for use. Follow these steps:
1. Give your workspace a name and provide a description about the domain to easily remember it.
2. Choose the language of your trained documents and dictionaries.
3. Optional: If you want to change the tokenizer that is used by the application from the default
machine learning-based tokenizer, expand the Advanced Options section and select
Dictionary-based tokenizer. For more information, see the References for this slide.
4. Optional: You can add project manager role, but because you have a Lite plan subscription,
skip this step. You cannot add other users. As an administrator, you can perform all the tasks
that a project manager typically performs.
References:
https://console.bluemix.net/docs/services/watson-knowledge-studio/create-project.html#create-proj
ect
https://www.youtube.com/watch?v=EQcEk2TX79c

© Copyright IBM Corp. 2018, 2019 9-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Workspace resources
• You add the following types of resources to the workspace:
ƒ Type system
ƒ Dictionaries
ƒ Documents
• The resources are either created or uploaded for training the models.
• Each of these resources may be used differently depending on the
model type.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-15. Workspace resources

The Knowledge Studio workspace contains the following types of resources:

• Type System: Defines the entities and relationships between entities that matter to you.
• Dictionaries: Group words and phrases that should be treated equivalently by a model.
• Documents: Serve a different purpose depending on whether you are creating a machine
learning model or a rule-based model.
The resources are either created or uploaded to train the models.
Each of these resources may be used differently depending on the model type.
Reference:
https://console.bluemix.net/docs/services/watson-knowledge-studio/artifacts.html#artifacts

© Copyright IBM Corp. 2018, 2019 9-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Type system
• Defines entities and relationships between entities that are interesting
for your domain:
ƒ Mentions. Example: “Watson”, “IBM”.
ƒ Entities types: Example: “PERSON”, “ORGANIZATION”.
ƒ Relation types: Example: founderOf, employedBy.
• Controls how content can be annotated.
• Can be created from scratch or uploaded from an existing type system.
• If you create a type system from scratch, define it directly in the
Knowledge Studio editor.
• To avoid visual overload for human annotation, define no more than 50
entity types and 50 relation types.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-16. Type system

A type system defines things that are interesting in your domain content that you want to label with
an annotation:
• Mentions: A mention is any span of text that you consider relevant in your domain data. For
example, “President Obama” or “IBM”.
• Entities types: Categorize a real-world thing. An entity mention is an example of a thing of that
type. For example, the mention President Obama can be annotated as a PERSON entity type.
The mention IBM can be annotated as an ORGANIZATION entity type.
• Relation types: Define a binary and ordered relationship between two entities. For a relation
mention to exist, the text must explicitly define the relation and bind mentions of the two entities
together, and must do so within a single sentence. For example, the sentence “Mary works for
IBM” is textual evidence of the employedBy relation type.
The type system controls how content can be annotated by defining the types of entities that can be
labeled and how relationships among different entities can be labeled. The model process manager
typically works with subject matter experts for your domain to define the type system.
In Knowledge Studio, you can create a type system from scratch or upload one from an existing
type system. To start a workspace, you might want to upload a type system that was created for a
similar domain. You can then edit the type system to add or remove entity types or redefine the
relationship types.

© Copyright IBM Corp. 2018, 2019 9-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Knowledge from Language Understanding and Extraction type system

• The Knowledge from Language Understanding and Extraction (KLUE)

is a sample type system that will be used in exercises.
• It was derived by IBM Research based on the analysis of collections of
news articles.
• Many industries publish dictionaries or ontologies of domain-specific
terminology, such as metallurgy, geology, market intelligence, life
science, electronic health records, and oncology.
• Consider referencing this type of resource to get an idea of the types of
entities you might want to define in your own type system.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-17. Knowledge from Language Understanding and Extraction type system

A sample type system based on the KLUE type system is provided for you to use with the
Knowledge Studio exercises.
KLUE stands for Knowledge from Language Understanding and Extraction and was derived by IBM
Research based on the analysis of collections of news articles.
Open the JSON KLUE type system from:
https://watson-developer-cloud.github.io/doc-tutorial-downloads/knowledge-studio/en-klue2-types.j
son
Show the structure of the KLUE type system to students mainly entityTypes and relationshipTypes
Show students “entityTypes” in JSON, Open number 24 and show students “PEOPLE” entity, and
number 25 showing “EVENT_VIOLENCE” entity. Remind them that a type system defines the entity
types that we are interested in detecting in our data.
Show students “relationshipTypes” in JSON, open number 2, it has a source entity type
(represented by the id of that entity as was previously defined for entity types) and a target entity
type and the label or name of the relationship that we are interested in which in this case is
ownerOf.

© Copyright IBM Corp. 2018, 2019 9-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
Many industries, such in domains like metallurgy, geology, market intelligence, life science,
electronic health records, and oncology publish dictionaries or ontologies of domain-specific
terminology. Consider referencing this type of resource to get an idea of the types of entities you
might want to define in your own type system.

© Copyright IBM Corp. 2018, 2019 9-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Dictionary
• A dictionary groups words and phrases that should be treated
equivalently by a model. Example:
ƒ September, Sept, Sep.
ƒ Monday, Tuesday, Wednesday (DAY_OF_WEEK).
• Dictionaries help the Knowledge Studio machine learning models to
understand the language of the domain.
• You can create dictionaries in Knowledge Studio:
ƒ Manually by adding individual entries.
ƒ Upload several types of dictionary files.
• Several general-purpose dictionaries are built in to the application.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-18. Dictionary

Dictionaries
In machine learning, a dictionary groups words and phrases that share something . An entry in the
dictionary does not mean that all words in the entry mean the same thing, but that the words are to
be treated equivalently by a model.
A dictionary is a list of words or phrases that are equivalent for information-extraction purposes,
meaning that they are interchangeable for the purposes of identifying entity and relation mentions.
Consider this example: A dictionary entry contains the seven days of the week. To annotate a
document, a human annotator assigns the entity type DAY_OF_WEEK to mentions of Monday and
Friday in the text. Because the dictionary equates the seven days of the week, it helps ensure that
a machine learning model correctly annotates occurrences of Tuesday, Wednesday, and the other
days of the week in unseen documents at run time. In addition, equating these words also benefits
information extraction in the surrounding text. What the machine learning model learns from
training examples about the texts near Monday and Friday is applied to texts that the machine
learning model sees near other days of the week because the dictionary states that these terms are
equivalent for information-extraction purposes.

© Copyright IBM Corp. 2018, 2019 9-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
You do not need to create a dictionary that contains days of the week information. Several
general-purpose dictionaries are built in to the application. Other built-in dictionaries include
countries, place names, number words, animals, plants, diseases, measurement words (such as
ounce and meter), and salutation title words (such as Mr. and Mrs.). You cannot disable or edit
built-in dictionaries.

© Copyright IBM Corp. 2018, 2019 9-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Dictionary usage
• Adding dictionaries is optional and may be used in two ways:
ƒ Machine learning usage: Used by the machine learning model to provide
words or phrases that are equivalent for information-extraction purposes.
ƒ Pre-annotation usage: Used during pre-annotation to bootstrap the
annotation effort.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-19. Dictionary usage

Adding dictionaries is optional and may be used in two ways:

• Machine learning usage: The machine learning model does not assume that a mention has a
specific entity type just because the mention matches an entry in a dictionary that is associated
with that entity type. It accounts for that information, but treats it as one piece of information
among other pieces of information that it gathers through linguistic analysis. In fact, if none of
the terms in a dictionary occur in the ground truth documents, then the dictionary is not used at
all by the machine learning model.
• Pre-annotation usage: Dictionaries are important to the following pre-annotation processes:
▪ Dictionary pre-annotator: You associate a dictionary with an entity type from the type system
when you run the dictionary pre-annotator.
▪ Rule-based model: You can optionally associate a dictionary with a rule class. Classes are
then mapped to entity types from the type system when you run the rule-based model to
pre-annotate documents. As a result, dictionary terms are, although circuitously, mapped to
entity types for the rule-based model also.

© Copyright IBM Corp. 2018, 2019 9-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
In both cases, the dictionaries provide terms that the system can find and annotate as
mentions. It assigns to each mention the entity type that is associated with the dictionary that
contains the term. When a human annotator begins work on new documents that were
pre-annotated, many mentions are already annotated based on the dictionary entries. The
human annotator thus has more time to focus on assigning entity types to mentions that require
deeper analysis.
Reference:
https://console.bluemix.net/docs/services/watson-knowledge-studio/dictionaries.html#dictionaries

© Copyright IBM Corp. 2018, 2019 9-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

CSV file dictionary

• The standard dictionary format.
• The maximum size of a CSV file that you can upload is 1 MB.
• The first row in the file must specify the following column headers:
lemma,poscode,surface
• The remaining lines in the file specify the dictionary entries, where:
ƒ Lemma: Specifies the most representative word form for the entry.
ƒ Poscode: Specifies a code that identifies the part of speech.
ƒ Surface: Specifies equivalent terms, also called surface forms.
ƒ Example:

lemma,poscode,surface
IBM,3,IBM Corp.,IBM,International Business Machines
Department of Energy,3,DOE,Department of Energy
premium,4,premium,premium-grade

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-20. CSV file dictionary

Also referred to as the standard dictionary format, a dictionary in comma-separated value (CSV)
format is a file that you can edit after you upload it. The maximum size of a CSV file that you can
upload is 1 MB. If you have a larger dictionary file, then break the large file into multiple files and
upload them one at a time into a single dictionary in your Knowledge Studio workspace.
To summarize the requirements, you must use a text editor to create the CSV file, not software like
Microsoft Excel, and the file must use UTF-8 encoding that does not include the byte order mark
(BOM) at the start of the text stream.
• Lemma: Specifies the most representative word form for the entry.
• Poscode: Specifies a code that identifies the part of speech. This part of speech information is
used by the dictionary annotator to help with sentence tokenization.
Note: This code supports the scenario where you want to upload a large machine-generated
dictionary that does not include part of speech information in each entry. You can assign
unknown to all entries by default. Avoid using this code, if possible.
0 - Unknown
1 - Pronoun
2 - Verb
3 - Noun

© Copyright IBM Corp. 2018, 2019 9-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
4 - Adjective
5 - Adverb
6 - Adposition
7 - Interjection
8 - Conjunction
9 - Determiner
10 - Quantifier
In English, noun (3), verb (2), and adjective (4) are the most common parts of speech that are
used for dictionary entries.
• Surface
Specifies equivalent terms, also called surface forms. Repeat the lemma as a surface form and
use a comma to separate multiple surface forms. If a surface form includes a comma, enclose
the surface form in quotation marks.

© Copyright IBM Corp. 2018, 2019 9-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Documents
• Usage for a machine learning model:
ƒ Documents are used to train the machine learning model when they are
annotated.
ƒ Examples: Journal articles or other industry-specific texts that are related to
the domain for which the model is built.
• Usage for a rule-based model:
ƒ Add or upload documents from which you can draw patterns to define as
rules.
ƒ Add documents with linguistic patterns that illustrate the types of rules you
want to define.
• Documents that you add for defining rules are kept separate from
documents that you add for annotation.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-21. Documents

Documents are the main resources that are needed for custom model creation. Documents are
used for different purposes based on the model being created.
• For a machine learning model:
▪ Documents are used to train the machine learning model when they are annotated.
▪ Examples: Journal articles or other industry-specific texts that are related to the domain for
which the model is built.
• For a rule-based model:
▪ Add or upload documents from which you can draw patterns to define as rules.
▪ Add documents with linguistic patterns that illustrate the types of rules you want to define.
Documents that you add for defining rules are kept separate from documents that you add for
annotation.
References:
https://console.bluemix.net/docs/services/knowledge-studio/documents-for-annotation.html#docum
ents-for-annotation
https://console.bluemix.net/docs/services/knowledge-studio/rule-annotator-add-doc.html#wks_rule
_anno_add

© Copyright IBM Corp. 2018, 2019 9-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
9.3. Adapting the system to a new domain

© Copyright IBM Corp. 2018, 2019 9-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Adapting the system to a new

domain

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-22. Adapting the system to a new domain

© Copyright IBM Corp. 2018, 2019 9-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Topics
• IBM Watson Knowledge Studio overview
• Watson Knowledge Studio features
• Adapting the system to a new domain

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-23. Topics

© Copyright IBM Corp. 2018, 2019 9-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Model life cycle: End-to-end domain adaptation

• Adapting a system to a new domain, requires an iterative process with
continuous improvements to increase the performance of the system.
• The creation of a model is an iterative multiple-step process that
involves these stages:
1. Knowledge curation
2. Ground truth generation
3. Model development
4. Model evaluation
5. Model deployment

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-24. Model life cycle: End-to-end domain adaptation

Adapting a cognitive system to a new domain, requires an iterative process with continuous
improvements to increase the performance of the system. This iterative process aims to reach a
level of incremental accuracy performing activities such as adding new functionalities, testing the
system, identifying opportunities to improve the performance, doing headroom analysis, and finding
possible solutions for the most frequent errors. The process requires the collaboration of domain
experts, data scientists, natural language processing (NLP) experts, and machine learning
developers.
The creation of a model is an iterative multiple-step process that involves several stages:
knowledge curation, ground truth generation, model development, model evaluation, and model
deployment.
The diagram summarizes the interactions between these five stages of model development and the
typical activities that occur at each stage.
References:
http://www.redbooks.ibm.com/redbooks.nsf/redbookabstracts/sg248387.html?Open
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle

© Copyright IBM Corp. 2018, 2019 9-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Knowledge curation

• This stage refers to the process of selecting, collecting, preserving, and

maintaining content relevant to a specific domain.
• This stage is external to Knowledge Studio.
• Curation adds value to data: It transforms data into trusted information
and knowledge.
• Knowledge curation involves the following activities:
ƒ Ensuring that the selected documents are representative of the domain
content.
ƒ Ensuring that selected documents cover the entity types and relation types
that are defined in your type system.
ƒ Providing more documents for a complex type system, and fewer for a
simpler one.
ƒ Limiting each document to a page or two of content. This is a preferred
practice, especially in the early stages of model development.
ƒ Ensuring that the documents include variations in vocabulary and phrasing.
ƒ In the case of skewed frequency-of-occurrence of entity types and relation
types, trying to get at least 50 exemplars of each type.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-25. Knowledge curation

Curation adds value to data by transforming data into trusted information and knowledge. This
stage, which is external to Knowledge Studio, refers to the process of selecting, collecting,
preserving, and maintaining content relevant to a specific domain.
This is an important stage because the curated content is used as input in the following stage.
You must ensure that the collected content is representative of your domain content and of high
value to your application.
Ensure that the collected content covers the entity types and relation types that are defined in your
type system. Sometimes, even a representative small sample of documents in the domain of
interest is collected and the type system is modified and refined based on it.
Ensure that the data in the documents is distributed across all possible entity types, subtypes, and
roles, and the relationships between them. A goal to aim for is to have at least 50 annotations for
each entity type and 50 for each relation type in the document collection.
Strive to provide a set of documents that have a total size of about 300,000 words. Provide more
words for a complex type system, and fewer for a simpler one.

© Copyright IBM Corp. 2018, 2019 9-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
Limit each document to a page or two of content (fewer than 2,000 words, and closer to 1,000
words per document is best). In the early stages of model development, keeping each document
down to a few paragraphs is a preferred practice. A human annotator can mark mentions and
relations in a long document, but attempts to mark co-references across multiple pages might prove
unwieldy.
Documents should represent the breadth of the subject matter that the application covers, but in the
case of skewed frequency-of-occurrence of entity types and relation types, try to get at least 50
exemplars of each type, and more for entity types that have mentions that tend to be phrases.
For more information about limitations, requirements, and supported input formats, see
https://console.bluemix.net/docs/services/watson-knowledge-studio/create-project.html#machine-l
earning-model.
References:
https://github.com/IBM-Bluemix-Docs/watson-knowledge-studio/blob/master/documents-for-annota
tion.md
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS2

© Copyright IBM Corp. 2018, 2019 9-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Ground truth generation

• This stage refers to the use of Knowledge Studio tools and best
practices to produce a collection of vetted data called ground truth or
gold standard documents.
ƒ The ground truth is used to adapt a Watson solution to a particular domain.
• Ground truth generation involves the following activities:
1. SMEs creating or identifying the following resources for your domain:
> Annotation guidelines and example for human annotators.
> Type systems that define domain-specific objects and features.
> Dictionaries of terms that are to be treated as equivalent terms in your domain
content.
2. Creating a corpus of documents that are representative of your domain
content.
3. Pre-annotating documents based on the dictionaries that you add to a
Knowledge Studio workspace.
4. Annotating documents by human annotators. Documents are divided
among human annotators who then use the Knowledge Studio ground
truth editor to manually add annotations.
5. Comparing the human annotation results and resolving conflicts.
Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-26. Ground truth generation

This stage refers to the use of Knowledge Studio tools and best practices to produce a collection of
vetted data that can be used to adapt a Watson solution to a particular domain. The accuracy of this
vetted data, called ground truth or gold standard documents, is critical because inaccuracies in the
ground truth will correlate to inaccuracies in the applications that rely on it.
An essential part of teaching Watson about a new domain involves providing it with knowledge
about entities of interest in your domain content, the relationships between them, and how the
entities co-reference each other. Collecting this knowledge includes the following activities:
1. Involving domain subject matter experts to create the following resources, or to identify existing
resources that can be re-used or modified for your domain:
▪ Annotation guidelines and examples to help human annotators learn how words and
passages in your domain content are to be annotated.
▪ Type systems that define the domain-specific types (objects) and features (data
classifications) that can be discovered in your domain content through text analysis. The
type system controls the types of annotations that a human annotator can add to
documents.
▪ Dictionaries of terms that are to be treated as equivalent terms in your domain content.
2. Creating a corpus of documents that are representative of your domain content.

© Copyright IBM Corp. 2018, 2019 9-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
3. Pre-annotating documents based on the dictionaries that you add to a Knowledge Studio
workspace.
This is an optional activity to make the process of human annotation easier. Instead of starting
from scratch, it creates a base on which the human annotators can build.
After you create a machine learning model, you can use the model to pre-annotate new
documents that you add to the corpus. Pre-annotation is a process of machine-annotating a
document to the extent possible before a machine learning model is available to do so.
Pre-annotation can reduce human-annotation labor by replacing some human annotation
creation with mere verification of the correctness of machine annotation.
4. Annotating documents by human annotators. Documents are divided among human
annotators, who then use the IBM Watson Knowledge Studio ground truth editor tool to
manually add annotations to small sets of documents. Humans annotate mentions, relations,
and co-references. The annotated documents are used as training and testing data for the
machine learning model.
5. Comparing the human annotation results and resolving conflicts. Adjudication in this phase is
needed to ensure accurate and consistently annotated documents are promoted to ground
truth, where they can be used to train and test a machine learning model.
References:
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS2
https://github.com/IBM-Bluemix-Docs/watson-knowledge-studio/blob/master/documents-for-annota
tion.md
https://console.bluemix.net/docs/services/watson-knowledge-studio/documents-for-annotation.html
#documents-for-annotation

© Copyright IBM Corp. 2018, 2019 9-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Model development
• This stage refers to the use of Knowledge Studio tools to create the
model.
• After the ground truth is generated, the human annotation results are
used to train an algorithm for automatically adding annotations to large
collections of documents, such as collections that include millions of
documents.
• Model development involves the following activities:
1. Selecting the document sets that you want to use to train the model.
Note: Only documents that became ground truth through approval or adjudication can be used
to train the machine learning model.
2. Specifying the percentage of documents that are to be used as training
data, test data, and blind data.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-27. Model development

This stage refers to the use of Knowledge Studio tools to create a model. After establishing ground
truth, the human annotation results can be used to train an algorithm for automatically adding
annotations to large collections of documents, such as collections that include millions of
documents.
Model development involves the following activities:
1. Selecting the document sets that you want to use to train the model.
Note: Only documents that became ground truth through approval or adjudication can be
used to train the machine learning model.
2. Specifying the percentage of documents that are to be used as training data, test data, and
blind data.

© Copyright IBM Corp. 2018, 2019 9-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
The documents that you add to the system must be allocated to the following system-level data
sets when you create a machine learning model:
• Training set: A set of documents that was annotated through pre-annotation or by human
annotators that is used to train the model. The goal of the training set is to teach the machine
learning model about correct annotations, which includes teaching the model through text that
was not annotated.
• Test set: A set of annotated documents that is used to test the trained model. After you run a
test on the test set, perform a detailed diagnostic-purposed error analysis of the results. Close
analysis helps you find weaknesses in the current model that can be addressed.
• Blind set: A set of annotated documents that is set aside and used to test the system
periodically after several iterations of testing and improvement have occurred. To prevent
accuracy from being tainted (for example, by making changes based only on annotations in
known documents), blind data should be data that has not previously been viewed by users that
were involved with creating the model. Reported results should come only from tests that are
run on blind data. After you run a test on the blind set, look at only the most high-level scores,
such as the overall mention and relation F1 scores. You do not want to learn too many details
about the performance or it might influence the improvements that you choose to make to the
model.
The goal of Knowledge Studio is to enable large teams to work together to build models. As such, it
assumes that models are being produced by a team that includes a group of human annotators and
a separate person or group of people that builds and tests the model, and makes improvements to
it. Due to this assumption, the application is configured to push an equally proportioned grouping of
documents from a single document set into the test, train, and blind sets. However, if your team is
not segregated (for example, the people doing human annotation are also reviewing model test
results in detail), then you might need to change the allocation of documents in these sets to more
explicitly separate the documents that are being used in each one.
Why do I need a blind set?
Because you use test data to assess accuracy in detail, you get to know the documents and their
features after a while. For example, you start to know which entity types, relation types, and text
types in the documents are best understood by the machine learning model, and which are not.
This information is important because it helps you focus on making the right improvements, that is,
refining the type system, supplementing the training data to fill gaps, or adding dictionaries. As the
test documents are used iteratively to improve the model, they can start to influence the model
training indirectly. That is why the "blind" set of documents is so important.
You can review the annotations that are made on the test set. Infer which are undertrained entities
and cycle through the steps again to provide better training material for these entities.
References:
https://console.bluemix.net/docs/services/watson-knowledge-studio/train-ml.html#train-ml
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS3

© Copyright IBM Corp. 2018, 2019 9-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Model evaluation
• This stage refers to the use of Knowledge Studio tools to refine the
model and improve performance.
• Model evaluation involves the following activities:
1. Evaluating the results generated by the model against a test set of ground
truth documents:
• Accuracy analysis to identify the causes of annotation errors.
• Headroom analysis to assess which errors require focus and where model
refinements can yield the greatest impact.
2. Reviewing the annotations that were added by the trained model to
determine whether any adjustments must be made to the model to
improve its ability to find valid entity mentions, relation mentions, and
coreferences in the documents.
3. Making adjustments repeatedly to improve performance until a
satisfactory level of accuracy is achieved.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-28. Model evaluation

This stage refers to the use of Knowledge Studio tools to refine the model and improve
performance. The results generated by the model are evaluated against a test set of ground truth
documents.
• Accuracy analysis identifies the causes of annotation errors.
• Headroom analysis helps you assess which errors require focus and where model refinements
can yield the greatest impact.
After you determine areas in which the model is having trouble, take steps to improve its
performance.
Adjustments can be made repeatedly to improve performance until a satisfactory level of accuracy
is achieved.
References:
https://console.bluemix.net/docs/services/watson-knowledge-studio/evaluate-ml.html#evaluate-ml
https://console.bluemix.net/docs/services/watson-knowledge-studio/improve-ml.html#improve-ml
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS4

© Copyright IBM Corp. 2018, 2019 9-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Model deployment
• This stage refers to exporting components that
enable the model to run in machine learning
runtime environments and making the model
accessible to other Watson applications.
• You can deploy the machine learning model for
use by:
ƒ Watson Natural Language Understanding
ƒ Watson Discovery
ƒ Watson Explorer
• Model deployment involves the following
activities:
1. Creating a snapshot of the current model.
2. Deploying the model to Watson Discovery or
Watson Natural Language Understanding services
3. Exporting the machine learning model so it can be
used in Watson Explorer (optional).

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-29. Model deployment

This stage refers to exporting components that enable the model to run in machine learning runtime
environments and making the model accessible to other Watson cognitive applications.
When you are satisfied with the performance of the model, you can leverage the machine learning
model that you trained with Knowledge Studio by making it available for use by:
• IBM Watson Natural Language Understanding service
• IBM Watson Discovery service
• IBM Watson Explorer
You can deploy or export a machine learning model. A dictionary or Natural Language
Understanding pre-annotator can only be used to pre-annotate documents within Knowledge
Studio.

© Copyright IBM Corp. 2018, 2019 9-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
Model deployment involves the following activities:
1. Creating a snapshot of the current model. This versions the model, which enables you to
deploy one version, while you continue to improve the current version. The option to deploy
does not appear until you create at least one version.
2. Deploying the model to Watson Discovery or Watson Natural Language Understanding
services.
3. Exporting the machine learning model so it can be used in Watson Explorer. This step is not
available for Lite IBM Cloud accounts.
Reference:
https://console.bluemix.net/docs/services/watson-knowledge-studio/annotate-documents.html#wks
_lifecycle__wks_lifecycleS5

© Copyright IBM Corp. 2018, 2019 9-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

End-to-end domain adaptation wrap-up

Knowledge
curation

Ground truth Model

generation deployment

Model Model
development evaluation

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-30. End-to-end domain adaptation wrap-up

The following points summarize the end-to-end domain adaptation process with Watson
Knowledge Studio:
• Adapting an AI system to a new domain, requires an iterative process with continuous
improvements to increase the performance of the system. This iterative process aims to reach a
level of incremental accuracy performing activities such as adding new functionalities, testing
the system, identifying opportunities to improve the performance, doing headroom analysis,
and finding possible solutions for the most frequent errors. The process requires the
collaboration of domain experts, data scientists, natural language processing (NLP) experts,
and machine learning developers.
• The creation of a model is an iterative multiple-step process that involves several stages:
knowledge curation, ground truth generation, model development, model evaluation, and model
deployment to runtime environments.
• Some tasks are performed outside Knowledge Studio and involve human experts to perform
activities to ensure that the collected data that will be used to train the model is relevant to the
domain, of high quality, and includes the right amount of representative documents.

© Copyright IBM Corp. 2018, 2019 9-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty
• Knowledge Studio provides tools and artifacts to:
▪ Guide human annotators while performing manual annotations.
▪ Pre-annotate documents to bootstrap human annotations.
▪ Evaluate annotations by multiple human annotators and generate the ground truth for your
domain.
▪ Create models.
▪ Evaluate the performance of the trained model.
▪ Deploy the model to Watson Discovery and Watson Natural Language Understanding or
export the model for use in Watson Explorer.
• Domain adaptation is a continuous improvement process which requires an ongoing effort to
improve the performance of the model. Domain adaptation is the primary purpose of Knowledge
Studio.

© Copyright IBM Corp. 2018, 2019 9-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Unit summary
• Describe IBM Watson Knowledge Studio.
• List the Watson services that are trained by Knowledge Studio.
• List the Knowledge Studio workspace resources.
• Explain the process to build Knowledge Studio models that can be
deployed and used with other Watson services.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-31. Unit summary

© Copyright IBM Corp. 2018, 2019 9-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Review questions
1. True or False: Rule-based models are efficient for complex
text extraction that has variations.
2. ______ defines entities and relationships between entities
that are interesting for your domain (mentions, entity types,
relation types).
A. Dictionary
B. Type system
C. Pre-annotation
D. Ground truth
3. The following Watson service cannot be trained by using
Knowledge Studio.
A. Watson Natural Language Classifier
B. Watson Natural Language Understanding
C. Watson Discovery
4. True or False: A ruled based model can be used to pre-
annotate documents to speed up the human annotation
process.
Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-32. Review questions

1. False. Rule-based models are efficient for recognizing patterns in unstructured data. Machine
learning models are efficient for complex text extraction.
2. B. Type system.
3. A. Natural Language Classifier.
4. True.

© Copyright IBM Corp. 2018, 2019 9-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Review questions (cont.)

5. ____ groups words and phrases that should be treated

equivalently by a model.
A. Ruled-based model
B. Ground truth
C. Dictionary
D. Machine learning model
E. Type system

6. ___ is a collection of vetted data used to adapt a Watson

solution to a particular domain.
A. Ruled-based model
B. Ground truth
C. Dictionary
D. Machine learning model
E. Type system

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-33. Review questions (cont.)

5. C. Dictionary.
6. B. Ground truth.

© Copyright IBM Corp. 2018, 2019 9-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Review answers
1. True or False: Rule-based models are efficient for complex
text extraction that has variations.
2. ______ defines entities and relationships between entities
that are interesting for your domain (mentions, entity types,
relation types).
A. Dictionary
B. Type system
C. Pre-annotation
D. Ground truth
3. The following Watson service cannot be trained by using
Knowledge Studio.
A. Watson Natural Language Classifier
B. Watson Natural Language Understanding
C. Watson Discovery
4. True or False: A ruled based model can be used to pre-
annotate documents to speed up the human annotation
process.
Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-34. Review answers

1. False. Rule-based models are efficient for recognizing patterns in unstructured data. Machine
learning models are efficient for complex text extraction.
2. B. Type system.
3. A. Natural Language Classifier.
4. True.

© Copyright IBM Corp. 2018, 2019 9-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Review answers (cont.)

5. ____ groups words and phrases that should be treated

equivalently by a model.
A. Ruled-based model
B. Ground truth
C. Dictionary
D. Machine learning model
E. Type system

6. ___ is a collection of vetted data used to adapt a Watson

solution to a particular domain.
A. Ruled-based model
B. Ground truth
C. Dictionary
D. Machine learning model
E. Type system

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-35. Review answers (cont.)

5. C. Dictionary.
6. B. Ground truth.

© Copyright IBM Corp. 2018, 2019 9-49

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Exercise: Creating a machine

learning model with Watson
Knowledge Studio

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-36. Exercise: Creating a machine learning model with Watson Knowledge Studio

© Copyright IBM Corp. 2018, 2019 9-50

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 9. Introduction to IBM Watson Knowledge Studio

Uempty

Exercise objectives
• This exercise helps you understand the process for building a
machine learning model that you can later deploy and use with
other Watson services.
• After completing this exercise you should be able to:
ƒ Create a workspace for Knowledge Studio.
ƒ Configure the workspace resources.
ƒ Create document sets.
ƒ Pre-annotate documents.
ƒ Create tasks for human annotators.
ƒ Analyze the inter-annotator agreement and adjudicate conflicts.
ƒ Create machine learning models.
ƒ Deploy the model to Watson Natural Language Understanding or
Watson Discovery.

Introduction to IBM Watson Knowledge Studio © Copyright IBM Corporation 2019

Figure 9-37. Exercise objectives

After completing this exercise you should be able to:

• Create a workspace for Knowledge Studio.
• Configure the workspace resources.
• Create document sets.
• Pre-annotate documents.
• Create tasks for human annotators.
• Analyze the inter-annotator agreement and adjudicate conflicts.
• Create machine learning models.
• Deploy the model to Watson Natural Language Understanding or Watson Discovery.

© Copyright IBM Corp. 2018, 2019 9-51

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Unit 10. Introduction to chatbots

Estimated time
00:30

Overview
This unit provides a high level introduction to chatbots, chatbot applications, and guidelines to
consider when designing a chatbot.

© Copyright IBM Corp. 2018, 2019 10-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Unit objectives
• Explain what a chatbot is.
• Describe the common applications of chatbots.
• Identify factors that drive the growing popularity of chatbots.
• Recognize the guidelines to consider when designing a chatbot.
• List examples of tools and services that you can use to create chatbots.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 10-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
10.1. Chatbots overview

© Copyright IBM Corp. 2018, 2019 10-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots overview

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-2. Chatbots overview

© Copyright IBM Corp. 2018, 2019 10-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Topics
• Chatbots overview
• Chatbots design
• Chatbots tools and services

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-3. Topics

© Copyright IBM Corp. 2018, 2019 10-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

What is a chatbot
• Software that interacts with the user in natural language.
• The application can have a chat interface.
• The conversation medium may be in text, speech, or both.
• Some example applications are customer support, sales activities, or
entertainment.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-4. What is a chatbot

A chatbot is software that interacts with the user through a chat interface by using natural language.
The conversation might be in text, speech, or both. The chatbot chats with the user to assist with
applications like customer support, sales activities, or entertainment.

© Copyright IBM Corp. 2018, 2019 10-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots in the industry

Apple Siri, Microsoft Cortana, Google Assistant, and Amazon Alexa:
ƒ Interact by using natural language and often in the form of speech.
ƒ Support functions like setting alarms, running searches, and retrieving
real-time information like news.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-5. Chatbots in the industry

There are many examples of chatbots:

Siri: The intelligent assistant of Apple iPhone. Siri can help you with your schedule and find the
nearest restaurant or movies that are available to watch.
Microsoft Cortana: Supported on various Microsoft Windows platforms. Also supported on
Android and iOS. It can set reminders and answer questions by using information from the Bing
search engine.
Google Assistant: Available on mobile and smart home devices. It provides the same functions
that Google does: Searches the internet, schedules events and alarms, adjusts hardware settings
on the user's device, and shows information from the user's Google account.
Amazon Alexa: Plays music and audiobooks, supports to-do lists, sets alarms, provides news and
other real-time information like weather updates, traffic, and sports. Alexa can also control different
smart devices that are part of a home automation system. You can give voice commands to control
your home automation system like “Alexa, turn off the light in the living room.”.
References:
https://en.wikipedia.org/wiki/Google_Assistant
https://en.wikipedia.org/wiki/Cortana
https://en.wikipedia.org/wiki/Amazon_Alexa

© Copyright IBM Corp. 2018, 2019 10-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots in the industry (cont.)

IBM Watson Assistant is tailored for domain-specific use cases.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-6. Chatbots in the industry (cont.)

Another example of a chatbot is one that supports customers with their inquiries or even helps
junior customer support agents with their job. IBM uses Watson technology (Watson Assistant) to
create chatbots for those purposes.
References:
https://www.ibm.com/us-en/marketplace/watson-assistant-for-automotive
https://www.ibm.com/ro-en/marketplace/watson-assistant-for-industry

© Copyright IBM Corp. 2018, 2019 10-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot history
• Bots passing the Turing test.
• ELIZA and PARRY did not use speech.
• SmarterChild was the predecessor to Siri, and was created by
ActiveBuddy, Inc.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-7. Chatbot history

1950s: The Turing test

The Turing test by Alan Turing was introduced as a standard of intelligence.
The standard is based on the capability of the computer program to impersonate or mimic a human
in real time through a written conversation with a human judge. If the judge cannot distinguish
between the program and a real human based on the conversation alone, the program passes the
Turing test. Many programmers took the Turing test as a challenge.
1966: ELIZA
In 1966, Metzenbaum’s program ELIZA tricked users into believing that they were having a
conversation with a human. ELIZA passed the Turing test.
1972: PARRY
Another chatbot was invented around 1972 that was called PARRY. PARRY was more advanced
than ELIZA. However, both ELIZA and PARRY could have a conversation only through text (not
speech). Advances in natural language processing have led to the emergence of more capable
chatbots since then.

© Copyright IBM Corp. 2018, 2019 10-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
2001: SmarterChild
In 2001, SmarterChild emerged. It was a chatbot that was used across SMS networks. It took
advantage of the popularity of SMS and added the capability to understand natural language. It
relied on database access for news, sports, entertainment, and other various topics. It is
considered the precursor to Siri.
2006: IBM Watson
In 2006, IBM Watson started initial test runs. In 2011, Watson competed on the Jeopardy! quiz TV
show. It understood and answered trivia questions, and won against human contestants (the
Jeopardy! champions).
2010: Siri
Siri emerged in 2010 as a personal assistant feature of Apple iOS. Siri can search for answers on
the web, create reminders, alarms, and events, call people, and much more.
2012: Google Now
In 2012, Google Now emerged, appearing as a feature in Google search. It delivered information to
users based on predictions of what they might be interested in knowing.
2015: Amazon Alexa and Microsoft Cortana
In 2015, Amazon Alexa, the virtual assistant behind Amazon Echo, and Microsoft Cortana
emerged.
2016: Chatbots
Facebook started a messaging platform enabling developers to create chatbots that can interact
with Facebook users. Today, there are more than 33,000 chatbots on Facebook Messenger alone.

© Copyright IBM Corp. 2018, 2019 10-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Why now
• Rising popularity and high usage of messenger applications, such as
WhatsApp, Facebook Messenger, and Slack
• Recent breakthroughs in the AI field
• Advancements in speech recognition
• Growing popularity of cloud computing and APIs

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-8. Why now

It seems that chatbots have become popular in recent years. Why now?
There are different reasons for the increase in the prevalence of chatbot:
• Rising popularity and high usage of messenger applications, such as WhatsApp, Facebook
Messenger, and Slack.
• Recent breakthroughs in the AI field make it possible to develop intelligent chatbots that can
communicate with users in human language and learn from their interaction with users.
Chatbots can learn over time to provide more accurate and intelligent responses.
• Advancements in speech recognition make it possible to take human speech as input and
enable users to have more natural interaction with computers.
• The growing popularity of cloud computing and APIs that provide integration capabilities make it
possible for AI vendors to make AI services easily available to developers on the cloud.
Developers can integrate chatbots into various applications and ensure reliable communication
between the chatbot and the application by using APIs.

© Copyright IBM Corp. 2018, 2019 10-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Popular chatbots
• DoNotPay chatbot for legal advice by Joshua Browder.
• Joshua Browder was named “Robin Hood of the internet” by the BBC.
• He used the IBM Watson Assistant service to improve the chatbot’s
accuracy by 30%.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-9. Popular chatbots

The DoNotPay chatbot is a popular chatbot. It was created by a 19-year old Stanford student who is
named Joshua Browder, whom is called “Robin Hood of the internet” by the BBC.
Browder used a natural language interface to gather the data that is needed to complete the form.
He also used the IBM Watson Assistant service to improve that chatbot’s accuracy by 30%.

© Copyright IBM Corp. 2018, 2019 10-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Popular chatbots (cont.)

• Woebot in the medical domain.
• “Create the experience of a therapeutic conversation for all of
the people that use the bot.”

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-10. Popular chatbots (cont.)

Woebot was created by a team of Stanford psychologists and AI experts.

Woebot uses short chat conversations, sentiment and tone analysis, and word games to help
people who are looking for inexpensive therapy. The mission of the creators of Woebot is “to make
mental health radically accessible to everyone”.
Woebot uses a combination of natural language processing, therapeutic expertise, personalized
content, and a sense of humor to “create the experience of a therapeutic conversation for all of the
people that use the bot.”

© Copyright IBM Corp. 2018, 2019 10-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
10.2. Chatbots design

© Copyright IBM Corp. 2018, 2019 10-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots design

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-11. Chatbots design

© Copyright IBM Corp. 2018, 2019 10-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Topics
• Chatbots overview
• Chatbots design
• Chatbots tools and services

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-12. Topics

© Copyright IBM Corp. 2018, 2019 10-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design
The basic goals of conversational interaction for chatbots are:
• Help users.
• Manage user expectations.
• Achieve the purpose of the solution.
• Keep the user engaged.
• Extract insights about the users.
• Reinforce the brand of the client.
• Increase sympathy and forgiveness in users.
• Make the solution look clever.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-13. Chatbot design

Conversational interaction in the chat between the chatbot and the user takes place by exchanging
natural language messages. Conversational interaction has an important role to play because it
must help the customer understand how the chatbot can help them while managing expectations.
It is important to design the conversation correctly and appropriately for the type of chatbot solution
and target audience. Not all solutions need the same amount of conversational interaction, but if
you do not deliberately design the conversational interaction, you will not fully realize the potential
of the solution to address the needs of your clients. If clients do not see enough value from the
chatbot solution, they are unlikely to continue to use it.
The basic goals of conversational interaction are:
• How to help users and manage their expectations.
• Help achieve the purpose of the solution and drive value.
• Encourage the user to keep using the chatbot.
• Derive usable insights about the users.
• Reinforce the brand of the client.
• Increase sympathy and forgiveness in users.
• Make the solution look clever.

© Copyright IBM Corp. 2018, 2019 10-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
To achieve these goals, the dialog must be carefully designed to use the appropriate language and
a suitable approach. Designing the chatbot is the part that is most removed from development. The
result of this design is the overall impression of the chatbot on the user.
Here are key factors to consider in the conversational design:
• Positioning
• Tone and personality

© Copyright IBM Corp. 2018, 2019 10-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning

Positioning
The positioning of the chatbot is a collective term that covers these three
aspects:

• Purpose
• Viewpoint
• Proactivity

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-14. Chatbot design: Positioning

To achieve your chatbot design goals, you must define different aspects about how to design your
chatbot .
The first concept to consider is positioning. Positioning determines how the solution should relate to
the user, and behave when interacting with the user. The positioning of the chatbot is a collective
term that covers these three aspects:
• Purpose
• Viewpoint
• Proactivity

© Copyright IBM Corp. 2018, 2019 10-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning (cont.)

Purpose: What is the purpose of the solution?
Examples:
• Clarify or answer the user’s questions.
• Guide users to find the information they are looking for.
• Help users to complete a process.
• Collect the information that is needed to report a problem.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-15. Chatbot design: Positioning (cont.)

Purpose: What is the purpose of the solution?

A conversational interaction should always have a clear purpose, that is, a well-defined job to do.
For example:
• Clarify or answer the user’s questions.
• Guide users to find the information they are looking for.
• Help users to complete a process.
• Collect the information that is needed to report a problem.
The purpose is the “job description” of the chatbot.
Chatbots, unlike standard application UI, tend to humanize interactions and they should be tailored
to the needs of the users.

© Copyright IBM Corp. 2018, 2019 10-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning (cont.)

Viewpoint: What role should the solution play in the relationship between
the client and the user?
Examples: Assistant, friend, coach, motivator, salesperson, and others

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-16. Chatbot design: Positioning (cont.)

Viewpoint:
Viewpoint is the role that the chatbot solution should adopt in relation to the end user. As a
designer, ask yourself:
• Who is the audience? (for example, students, prospect clients, users of your product, tourists,
and so on)
• Who does the chatbot speak on behalf of? (for example, an employee who speaks on behalf of
the company, as an advocate or friend to the user who speaks on behalf of the tourism
organization, a tutor or teacher who speaks on behalf of a school or university, and so on.)
The relationship that the bot will have with the user should be decided upon in light of achieving the
purpose previously determined: Does the chatbot represent a salesperson? an entertainer? a
teacher? an enforcer or regulator? a companion or friend?
Viewpoint can be determined through these questions:
• What role should the solution play in the relationship between the client and the user?
• Should the chatbot present itself as an employee who speaks on behalf of the client and is
aligned with the client interests?
• Should the chatbot present itself as an advocate or friend to the user who can access the
client’s information to help the user?

© Copyright IBM Corp. 2018, 2019 10-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
Some examples of roles or viewpoint are:
• Assistant
• Friend
• Coach
• Motivator
• Salesperson
Another question is, who is the audience? Are they students, prospect clients, users of a product, or
others?
Reference:
https://www.ibm.com/blogs/watson/2017/12/3-types-of-business-chatbots-you-can-build/

© Copyright IBM Corp. 2018, 2019 10-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning (cont.)

Proactivity:
• Level of proactiveness or reactiveness when engaging with user.
• A chatbot can be:
ƒ Proactive (lean forward): The chatbot reaches out to the user and
asks questions.
ƒ Reactive (lean backward): The chatbot waits for the user to ask a
question.
ƒ Combination: The chatbot uses both techniques.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-17. Chatbot design: Positioning (cont.)

Proactivity is the degree to which the solution proactively engages and guides the user instead of
reacting to the user, that is, waiting for the user to ask a question.
A chatbot can be:
• Proactive: The chatbot reaches out to the user by asking questions, offering information and
choices, and guiding the user through processes.
• Reactive: Apart from a welcome message (and perhaps one or two other statements), your
chatbot waits for the user to ask a question. It does not prompt, encourage, or suggest.
• Combination: In specific circumstances, the chatbot reaches out to the user, asking questions
and guiding the user through processes. At other times, the chatbot waits for the user to ask a
question.

© Copyright IBM Corp. 2018, 2019 10-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning (cont.)

• Example of a proactive chatbot:
ƒ Customer: When can I receive my new credit card?
ƒ Chatbot: An SMS will be sent to your phone after it is ready.
ƒ Chatbot: The bank is collaborating with XYZ to provide benefits to our credit
card users. Would you be interested in knowing more?

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-18. Chatbot design: Positioning (cont.)

Imagine a scenario where a chatbot is acting as a customer service employee on behalf of a bank.
The following conversation represents a proactive chatbot:
• Customer: When can I receive my new credit card?
• Chatbot: An SMS will be sent to your phone after it is ready.
• Chatbot: The bank is collaborating with XYZ to provide benefits to our credit card users. Would
you be interested in knowing more?
The chatbot answers when asked, but also reaches out to the customer and offers suitable
suggestions.

© Copyright IBM Corp. 2018, 2019 10-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Positioning (cont.)

• Example of a reactive chatbot:
ƒ Customer: When can I receive my new credit card?
ƒ Chatbot: An SMS will be sent to your phone after it is ready.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-19. Chatbot design: Positioning (cont.)

The following conversation represents a reactive chatbot:

• Customer: When can I receive my new credit card?
• Chatbot: An SMS will be sent to your phone after it is ready.
The chatbot waits for the customer’s question, and answers only when asked.

© Copyright IBM Corp. 2018, 2019 10-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality

• Represents the voice in which the chatbot solution speaks.
• Examples:
ƒ Informal and friendly tone: “Hi there, how can I help you?”
ƒ More formal, still friendly: “Good morning. How may I help you today?
ƒ Formal, not very friendly: “This is a service that is designed to answer your
questions. How may I assist you with your inquiries?”

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-20. Chatbot design: Tone and personality

Tone and personality: Represents the voice in which the chatbot solution speaks. Do not confuse
tone and personality with viewpoint, which is whom the chatbot speaks on behalf.
Examples:
• Informal and friendly tone: “Hi there, how can I help you?”
• More formal, still friendly: “Good morning. How may I help you today?”
• Formal, not very friendly: “This is a service that is designed to answer your questions. How may
I assist you?”

© Copyright IBM Corp. 2018, 2019 10-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality (cont.)

What happens if you do not define tone and personality?
The chatbot will still have them, but it likely will be incoherent, which leads
to a random user experience.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-21. Chatbot design: Tone and personality (cont.)

What happens if you do not define tone and personality?

All verbal expression has a tone, all conversation is held between two sides, with someone, or
something with a personality in mind.
If you do not define tone and personality, the chatbot will still have them, but if they are not
deliberately and explicitly determined the chatbot likely will be incoherent, which leads to a random
user experience.

© Copyright IBM Corp. 2018, 2019 10-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality (cont.)

• You can construct a complete character persona for your chatbot .
• A common feature that is often in chatbots is humor.
• Humor increases the user's understanding, forgiveness, and
satisfaction.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-22. Chatbot design: Tone and personality (cont.)

You should determine the kind of personality that your users like better or feel more comfortable
interacting with when designing your chatbot.
Personality is affected by the choice of words for the chatbot’s responses.
You can construct a complete character persona for your chatbot.
A common feature that is often in chatbots is humor. Humor can increase the user's understanding
and forgiveness when your chatbot cannot understand something. It might even delight the user
and increase their satisfaction with the chatbot.

© Copyright IBM Corp. 2018, 2019 10-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality for purpose

• Example 1: If the purpose is to engage users proactively and
encourage them to act, a friendly, informal tone will be more successful
than a formal or authoritative tone.
• Example 2: If the purpose is to provide information or guidance about a
serious topic, a casual, chatty tone might undermine the credibility of
the information that is provided.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-23. Chatbot design: Tone and personality for purpose

Here are two examples of tone and personality for the purpose:
• If the purpose is to engage users proactively and encourage them to act, a friendly, informal
tone will be more successful than a formal or authoritative tone.
• If the purpose is to provide information or guidance about a serious topic, a casual, chatty tone
might undermine the credibility of the information that is provided.

© Copyright IBM Corp. 2018, 2019 10-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality for viewpoint

• Example 1: If the viewpoint is that of an employee, the tone and
personality should closely reflect the client’s ideal staff member.
• Example 2: If the viewpoint is that of a partially or fully independent
advocate or guide for the user, then the tone and personality should not
be that of enforcer or authority figure. Instead, it should be more like an
advisor, assistant, or coach.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-24. Chatbot design: Tone and personality for viewpoint

Here are some examples for tone and personality for viewpoint:
• If the viewpoint is that of an employee, the tone and personality should closely reflect the
client’s ideal staff member.
• If the viewpoint is that of a partially or fully independent advocate or guide for the user, then the
tone and personality should not be that of enforcer or authority figure. Instead, it should be more
like an advisor, assistant, or coach.

© Copyright IBM Corp. 2018, 2019 10-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Tone and personality for proactivity

• If the solution is highly proactive, either an overly formal or overly
casual and chatty tone may have an unpleasant effect because the
former might feel artificial and the latter is likely to become annoying.
• Tone and personality for special cases: If a response uses offensive
language:
í The chatbot can shift to an “enforcer” viewpoint and adopt a more formal tone.
í You may keep a count of the number of sensitive inputs and respond with an
increasingly strong-worded response.
í You may shut down the chat (in the case of threats and offensive language).

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-25. Chatbot design: Tone and personality for proactivity

If the solution is highly proactive, either an overly formal or overly casual and chatty tone may
cause a negative reaction because the former might feel artificial and the latter is likely to become
annoying.
Consider the appropriate tone and personality for special cases. There might be special cases
where the tone response might differ from the rest of the solution. For example, if there are
responses that use offensive language:
• The chatbot can shift to an “enforcer” viewpoint and adopt a more formal tone.
• You may keep a count of the number of sensitive inputs and respond with an increasingly
strong-worded response.
• You may shut down the chat (in the case of threats and offensive language).

© Copyright IBM Corp. 2018, 2019 10-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbot design: Design issues

1. Understand the limitations of a chatbot.
2. Acknowledge limitations and do not be afraid to have the chatbot say,
“I don’t know”, and give some suggestions of questions that they can
ask.
3. Handle frustration. “I can see this isn’t going very well. Would you like
to talk to a real person?”

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-26. Chatbot design: Design issues

Some of the issues that developers or designers face while designing chatbots include the following
ones:
1. Trying to do too much within a single chatbot, which can lead to a loss of value: You must
understand the limitations of a chatbot. It must have a narrow scope that is well-defined and
well-bounded. It is not a chitchat.
2. Users will be disappointed by incorrect or nonsensical responses: To avoid this issue,
acknowledge limitations and do not be afraid to have the chatbot say, “I don’t know”, and give
some suggestions of questions that they can ask.
3. Detect frustration, and handle it: If the users are frustrated, this issue should be addressed. A
good example response can be: “I can see that this isn’t going very well. Would you like to talk
to a real person?” Some interactions are too complex for a software solution to handle.
Detecting situations that are out of the scope of your chatbot and handing them off to a human
quickly (before you waste the user’s time) is a better approach.

© Copyright IBM Corp. 2018, 2019 10-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
10.3. Chatbots tools and services

© Copyright IBM Corp. 2018, 2019 10-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots tools and services

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-27. Chatbots tools and services

© Copyright IBM Corp. 2018, 2019 10-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Topics
• Chatbots overview
• Chatbots design
• Chatbots tools and services

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-28. Topics

© Copyright IBM Corp. 2018, 2019 10-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Chatbots tools and services

Here are examples of some available tools and services:
• IBM Watson Assistant service
• Dialogflow
• Microsoft Language Understanding Intelligent Service (LUIS)
• ChatScript
• Chatfuel

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-29. Chatbots tools and services

You can create chatbots by using cognitive services to help you design how your chatbot
understands user’s input and replies to the user. You can also use software to configure a chatbot
that is already trained and programmed to answer specific questions from users in areas such as
customer support.
Here are examples of some available tools and services:
• IBM Watson Assistant service.
• Dialogflow: Google-owned developer of human-computer interaction technologies that are
based on natural language conversations.
• Microsoft Language Understanding Intelligent Service (LUIS).
• ChatScript: Written in C++.
• Chatfuel: A platform for creating AI chatbots for Facebook.

© Copyright IBM Corp. 2018, 2019 10-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty
References:
https://chatfuel.com/
https://en.wikipedia.org/wiki/ChatScript
https://dialogflow.com/
https://en.wikipedia.org/wiki/Dialogflow
https://www.luis.ai/

© Copyright IBM Corp. 2018, 2019 10-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Unit summary
• Explain what a chatbot is.
• Describe the common applications of chatbots.
• Identify factors that drive the growing popularity of chatbots.
• Recognize the guidelines to consider when designing a chatbot.
• List examples of tools and services that you can use to create chatbots.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-30. Unit summary

© Copyright IBM Corp. 2018, 2019 10-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Review questions
1. Chatbots can be used for:
A. Customer support
B. Entertainment
C. Sales assistant
D. All the above
2. True or False: Advancements in NLP and AI are key factors
in the emergence of chatbots.
3. True or False: A chatbot that reaches out to the user by
asking questions and offering information is considered
reactive by design.
4. True or False: There are two types of viewpoint: lean
forward and lean backward.

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-31. Review questions

1. D. All the above.

2. True.
3. False.
4. False.

© Copyright IBM Corp. 2018, 2019 10-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Review questions (cont.)

5. ___ is the role that the chatbot solution should adopt in
relation to the end user, for example customer support
operator, coach, friend, or teacher.
A. Viewpoint
B. Purpose
C. Positioning
D. Proactivity
6. Represents the voice in which the chatbot solution speaks,
for example, informal, friendly, or formal.
A. Viewpoint
B. Purpose
C. Tone and personality
D. Positioning
E. Proactivity

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-32. Review questions (cont.)

5. A. Viewpoint.
6. C. Tone and personality.

© Copyright IBM Corp. 2018, 2019 10-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Review answers
1. Chatbots can be used for:
A. Customer support
B. Entertainment
C. Sales assistant
D. All the above
The answer is D.
2. True or False: Advancements in NLP and AI are key factors
in the emergence of chatbots.
3. True or False: A chatbot that reaches out to the user by
asking questions and offering information is considered
reactive by design.
4. True or False: There are two types of viewpoint: lean
forward and lean backward.
False: There are two types of proactivity: lean forward and
lean backward.
Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-33. Review answers

1. D. All the above.

2. True.
3. False.
4. False. There are two types of proactivity: lean forward and lean backward.

© Copyright IBM Corp. 2018, 2019 10-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 10. Introduction to chatbots

Uempty

Review answers (cont.)

5. ___ is the role that the chatbot solution should adopt in
relation to the end user, for example customer support
operator, coach, friend, or teacher.
A. Viewpoint
B. Purpose
C. Positioning
D. Proactivity
6. Represents the voice in which the chatbot solution speaks,
for example, informal, friendly, or formal.
A. Viewpoint
B. Purpose
C. Tone and personality
D. Positioning
E. Proactivity

Introduction to chatbots © Copyright IBM Corporation 2019

Figure 10-34. Review answers (cont.)

5. A. Viewpoint.
6. C. Tone and personality.

© Copyright IBM Corp. 2018, 2019 10-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Unit 11. Introduction to IBM Watson

Assistant
Estimated time
01:00

Overview
This unit covers the core concepts that you need to understand to build a chatbot with IBM Watson
Assistant.

© Copyright IBM Corp. 2018, 2019 11-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Unit objectives
• Explain assistants and skills.
• Explain intents.
• Explain entities.
• Explain context variables.
• Describe how the nodes in a dialog are triggered.
• Describe how the dialog flow is processed.
• Describe the features that can be used to enrich the chatbot.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 11-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty
11.1. Chatbot components

© Copyright IBM Corp. 2018, 2019 11-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Chatbot components

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-2. Chatbot components

© Copyright IBM Corp. 2018, 2019 11-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Topics
• Chatbot components
• Watson Assistant components
• Enriching the chatbot

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-3. Topics

© Copyright IBM Corp. 2018, 2019 11-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Chatbot components
• Most chatbot functions are divided into:
ƒ Intents

ƒ Entities

ƒ Dialog

• The dialog component is optional because some chatbots are

developed to answer user questions in a question and answer manner
that is similar to the approach that is used to answer frequently asked
questions (FAQs).

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-4. Chatbot components

No matter what the specific purpose of your chatbot is, some core fundamentals are always
involved. Most chatbot functions are divided into:
• Intents
• Entities
• Dialog
Each of these functions will be explained in detail and how they apply to the IBM Watson Assistant
Service in the next section.
The dialog component is optional because some chatbots are developed to answer user questions
in a question and answer manner that is similar to the approach that is used to answer frequently
asked questions (FAQs).
These chatbots need to understand only what the user is asking and reply with the proper answer.
Chatbots that are meant to answer FAQs do not have to engage in a conversation with the user and
therefore they do not need a dialog component.

© Copyright IBM Corp. 2018, 2019 11-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty
11.2. Watson Assistant components

© Copyright IBM Corp. 2018, 2019 11-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-5. Watson Assistant components

© Copyright IBM Corp. 2018, 2019 11-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Topics
• Chatbot components
• Watson Assistant components
• Enriching the chatbot

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-6. Topics

© Copyright IBM Corp. 2018, 2019 11-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components

Watson Assistant main components:
• Assistants
• Skills
• Intents
• Entities
• Dialog

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-7. Watson Assistant components

The Watson Assistant main components are:

• Assistants
• Skills
• Intents
• Entities
• Dialog

© Copyright IBM Corp. 2018, 2019 11-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Assistant:
• A cognitive bot that you can customize for your business needs.
• Customize the assistant by adding one or more skills to it to satisfy your
customers' goals.
• The assistant can be deployed through multiple interfaces, including:
ƒ Messaging channels, like Slack and Facebook Messenger.
ƒ A simple chat widget on a website or on an
existing company web page.
ƒ A custom application, such as a mobile app or a
robot with a voice interface.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-8. Watson Assistant components (cont.)

Assistants
An assistant is a cognitive bot that you can customize for your business needs and deploy across
multiple channels to help your customers where and when they need it.
You customize the assistant by adding to it the skills that it needs to satisfy your customers' goals.
Add a dialog skill that can understand and address questions or requests with which your
customers typically need help. You provide information about the subjects or tasks that your users
ask about and how they ask about them, and the service dynamically builds a machine learning
model that is tailored to understand the same and similar user requests.
You can deploy the assistant through multiple interfaces, including:
• Existing messaging channels, such as Slack and Facebook Messenger.
• You can give your users access to the assistant through a simple chat widget that you publish to
a website or add to an existing company web page.
• You can design a custom application that incorporates it by making direct calls to the underlying
APIs.

© Copyright IBM Corp. 2018, 2019 11-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Skill (formerly Workspace):
• Sometimes referred to as dialog skills.
• Acts as a container for all of the artifacts and training data.
• A skill contains the following types of artifacts:
ƒ Intents
ƒ Entities
ƒ Dialog

• A skill uses the unique training data to build a machine learning model
that can recognize these and similar user inputs. Each time that you
add or change the training data, the training process is triggered to
ensure that the underlying model stays up-to-date.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-9. Watson Assistant components (cont.)

Skill
Formerly called Workspaces. It is sometimes referred to as dialog skill.
A skill acts as a container that contains the training data and logic that enables an assistant to help
your customers.
A skill contains the following types of artifacts:
• Intents
• Entities
• Dialog
As you add information, the skill uses this unique data to build a machine learning model that can
recognize these and similar user inputs. Each time that you add or change the training data, the
training process is triggered to ensure that the underlying model stays up-to-date as your customer
needs and the topics they want to discuss change.

© Copyright IBM Corp. 2018, 2019 11-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Intent:
• Represents the purpose of or goal of a user's input.
• Tends to be general, such as a question about business location or a
bill payment.
• For intent creation:
ƒ Plan the intents for application. Define an intent for each type of user request
that you want your application to support.
ƒ Teach Watson about your intents. Supply many examples of user input and
indicate the intents to which they map.

• In the tool, the name of an intent is always prefixed with ’#’. For
example, #payment or #inquiry.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-10. Watson Assistant components (cont.)

Intent
An intent represents the purpose of a user's input, such as a question about business locations or a
bill payment.
Plan the intents for an application: Consider what your customers might want to do and what you
want your application to be able to handle on their behalf. For example, you might want your
application to help your customers make a purchase. If so, you can add a #buy_something intent.
You define an intent for each type of user request that you want your application to support.
Teach Watson about your intents: After you decide the business requests that you want your
application to handle for your customers, you must teach Watson about them. For each business
goal (such as #buy_something), you must provide at least 10 examples of utterances that your
customers typically use to indicate their goal. For example, “I want to make a purchase.”

© Copyright IBM Corp. 2018, 2019 11-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty
Ideally, find real-world user utterance examples that you can extract from existing business
processes. The user examples should be tailored to your specific business. For example, if you are
an insurance company, your user examples might look more like this, “I want to buy a new XYZ
insurance plan.”
To train the dialog skill to recognize your intents, supply many examples of user input and indicate
to which intents they map. The examples that you provide are used by the service to build a
machine learning model that can recognize the same and similar types of utterances and map them
to the appropriate intent.
In the tool, the name of an intent is always prefixed with the # character.
Start with a few intents, and test them as you iteratively expand the scope of the application.

© Copyright IBM Corp. 2018, 2019 11-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Intent examples:
• “Good morning” -> #greeting.
• “Where can I find the nearest restaurant?” -> #location_info.
• “Where can I pay my electric bill?” -> #location_info.
• Remember: Intents represent what the user wants to achieve: a goal,
an action, or verbs.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-11. Watson Assistant components (cont.)

Intent examples:
• “Good morning” -> #greeting
• “Where can I find the nearest restaurant?” -> #location_info
• “Where can I pay my electric bill?” -> #location_info
Remember: Intents represent what the user wants to achieve: a goal, an action, or verbs.

© Copyright IBM Corp. 2018, 2019 11-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant intents features

Content catalog:
• An easy way to add common intents to your Watson Assistant dialog
skill.
• Contains prebuilt common intents that you can add to your application
rather than building your own.
• For example, most applications require a greeting intent that starts a
dialog with the user. You can add the General content catalog to add an
intent that greets the user and does other useful things, like end the
conversation.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-12. Watson Assistant intents features

A content catalog is provided that contains prebuilt common intents that you can add to your
application rather than building your own. For example, most applications require a greeting intent
that starts a dialog with the user. You can add the General content catalog to add an intent that
greets the user and does other useful things, like end the conversation.
Important: Content catalog intents are meant to provide a starting point, and not meant to be fully
built-out for production use. Review and expand on these intents to make them better suited to how
your application uses them.

© Copyright IBM Corp. 2018, 2019 11-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant intents features (cont.)

Content catalog

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-13. Watson Assistant intents features (cont.)

This slide shows the content catalog that is built into the Watson Assistant tool. The content catalog
provides some general categories, such as General and Bot Control, which are good starters for
anyone creating a chatbot. There also are starters for some use cases in certain industries, such as
Banking, e-commerce, Telco, and Insurance, or general use cases that are found in most
industries, such as Customer Care and Utilities. Within each category is a set of intents that is
related to that category, which you can choose and add. After adding them, you can customize
each intent by adding more examples to it or removing some examples.

© Copyright IBM Corp. 2018, 2019 11-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Entity
• Represents a term or object that is relevant to the user’s intent and that
provides a specific context for an intent.
• If intents represent verbs (the action a user wants to do), entities
represent nouns (the object of, or the context for, that action).
• By recognizing the entities that are mentioned in the user's input, the
service can reply with a more targeted response or perform a required
action.
• In the tool, the name of an entity is always prefixed with ’@’. For
example, @street or @contact_info.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-14. Watson Assistant components (cont.)

Entity
Entities represent information in the user input that is relevant to the user's purpose.
If intents represent verbs (the action a user wants to do), entities represent nouns (the object of, or
the context for, that action). For example, when the intent is to get a weather forecast, the relevant
location and date entities are required before the application can return an accurate forecast.
Entities represent a class of object or a data type that is relevant to a user’s purpose. By
recognizing the entities that are mentioned in the user's input, the service can reply with a more
targeted response or perform a required action.

© Copyright IBM Corp. 2018, 2019 11-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant entity evaluation

• The Assistant service looks for terms in the user input by using exact
matching of values, synonyms, or patterns that are defined for the
entities.
• Synonym entity:
ƒ Specify a bunch of synonyms, that is, words that have exact or similar
meanings.
ƒ For example, for the entity value Blue, its synonyms can be Aqua, Navy,
and Cyan.
• Pattern entity:
ƒ You specify a regular expression that defines the pattern for mentions.
ƒ For example, for email patterns such as [email protected], the pattern can be:

\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-15. Watson Assistant entity evaluation

The Assistant service looks for terms in the user input that match the values, synonyms, or patterns
that you define for the entity:
• Synonym entity: Synonyms are words or phrases that mean exactly or nearly the same as the
corresponding entity. You define a category of terms as an entity (color), and then one or more
values in that category (blue). For each value, you specify a bunch of synonyms (aqua, navy,
and cyan). At run time, the service recognizes terms in the user input that exactly match the
values or synonyms that you defined for the entity as mentions of that entity.
• Pattern entity: You define a category of terms as an entity (contact_info), and then define one
or more values in that category (email). For each value, you specify a regular expression that
defines the textual pattern of mentions of that value type. For an email entity value, you might
want to specify a regular expression that defines a [email protected] pattern.
This email regex example can capture all mentions of emails in their proper format.
At run time, the service looks for patterns matching your regular expression in the user input,
and identifies any matches as mentions of that entity.

© Copyright IBM Corp. 2018, 2019 11-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant entity evaluation (cont.)

System entity: A synonym entity that is prebuilt by IBM (such as numbers,
dates, or others).

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-16. Watson Assistant entity evaluation (cont.)

System entity: A synonym entity that is prebuilt for you by IBM. They cover commonly used
categories, such as numbers, dates, and times. You simply enable a system entity to start using it.

© Copyright IBM Corp. 2018, 2019 11-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant entities features

Fuzzy matching:
• Can be enabled in entity definitions.
• By enabling fuzzy matching, the service can recognize terms similar to
the entity value and synonyms without requiring an exact match.
• Detects entities in different grammatical forms. For example:
ƒ bananas > banana
ƒ running > run.
• Detects misspelled entities. For example:
ƒ girafe > giraffes.
• Detects partial matching.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-17. Watson Assistant entities features

Fuzzy matching
If you want the service to recognize terms with a syntax that is similar to the entity value and
synonyms that you specify but without requiring an exact match, enable the fuzzy matching
feature.
This feature is available for all supported languages of Watson Assistant.
Detects entities in different grammatical forms: If your entity value is banana and the user inputs
bananas, it can map them to each other.
Detects misspelled entities: If your entity value is giraffes and the user inputs girafe (misspelled),
the service can map them to each other.
Detects partial matching.

© Copyright IBM Corp. 2018, 2019 11-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant entities features (cont.)

Synonym recommendations
• The service can recommend synonyms for entity values.
• Used only for synonym entity values, not patterns.
• This feature finds related synonyms and uses natural language
processing techniques to identify words that are similar to the existing
synonyms in your entity value.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-18. Watson Assistant entities features (cont.)

Entity synonym recommendations

The Watson Assistant service can recommend synonyms for your entity values. The recommender
finds related synonyms based on contextual similarity that is extracted from a vast body of existing
information, including large sources of written text, and uses natural language processing
techniques to identify words that are similar to the existing synonyms in your entity value.
The figure shows some recommendations for the entity value “bird”.

© Copyright IBM Corp. 2018, 2019 11-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Dialog
• A dialog is a branching conversation flow that defines how your
application responds when it recognizes the defined intents and entities.
• The dialog is made up of nodes that are chained together in a tree
structure (graphically).
• Each node includes conditions for the node to be active, and also an
output object that defines the response that is provided.
• Think of the node as an if-then construction: If this condition is true,
then return this response.

User

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-19. Watson Assistant components (cont.)

Dialog
A dialog is a branching conversation flow that defines how your application responds when it
recognizes the defined intents and entities.
The dialog is made up of nodes that define steps in the conversation.
Dialog nodes are chained together in a tree structure (graphically).
Each node includes conditions for the node to be active, and also an output object that defines the
response that is provided.
Think of the node as an if-then construction: If this condition is true, then return this response.
Condition: Specifies the information that must be present in the user input for this node in the
dialog to be triggered.
Response: The utterance that the service uses to respond to the user.

© Copyright IBM Corp. 2018, 2019 11-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Dialog (cont.)
• A single node with one condition and response can handle simple user
requests.
• To handle more complex tasks, you can add child nodes to ask the user
for additional information.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-20. Watson Assistant components (cont.)

Dialog
A single node with one condition and response can handle simple user requests.
To handle more complex tasks, you can add child nodes to ask the user for additional information.
A child node is processed after its parent node. NODE 1 is the parent node for CHILD NODE 1 and
CHILD NODE 2.
Some useful definitions:
• A root node is a node that does not depend on other nodes. In our example, NODE 1 is a root
node.
• A child node is a node that depends on another node, its parent node. The parent node is
processed first, and based on that processing, the child node is either processed or not.

© Copyright IBM Corp. 2018, 2019 11-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Context variables
ƒ The dialog in a dialog skill is stateless. It does not retain information from one
interaction with the user to the next.
ƒ Context variables allow storing information that is passed back and forth
across different dialog nodes, and between the dialog and application.
ƒ A context variable is defined in a node. It can have a default value that can
be changed.
ƒ For example, if you identify the name of your user in the dialog flow, you can
store the information in a context variable and retrieve it anytime that you
want to call your user by name.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-21. Watson Assistant components (cont.)

Context: As in a real-life conversation, context matters. The dialog context is the mechanism for
passing information between the dialog and your application code. Context variables allow you to
store information that is passed back and forth across different dialog nodes. For example, if you
identify the names of your users in the conversation flow, you can store the information in the
context and retrieve it anytime that you want to call your user by name.

© Copyright IBM Corp. 2018, 2019 11-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Context variables (cont.)
ƒ Context variables (username variable) are stored in context objects that are
described as a JSON entry in the node.

"context": {
"username": "<? @sys-person.literal ?>"
}

ƒ In the tool, the context variable is always prefixed with ’$’, for example,
$username.
ƒ The context object can be handled in the context editor interface for
simplicity.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-22. Watson Assistant components (cont.)

In this JSON object, there is a context object that contains the context variable username. If you
identify the names of your users in the conversation flow, you can store the information in the
context variable username as defined and retrieve it anytime that you want to call your user by
name. This is a simple example. You can learn how to define different types of context variables at
https://console.bluemix.net/docs/services/assistant/dialog-runtime.html#context-var-json.

© Copyright IBM Corp. 2018, 2019 11-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Conditions
• Logical expressions that are evaluated to true or false.
• A node condition determines whether that node is used in the
conversation.
• Conditions usually evaluate the intents and entities that are identified in
the user responses, but they can also evaluate information that is
stored in the context.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-23. Watson Assistant components (cont.)

Conditions
Conditions are logical expressions that are evaluated to true or false. A node condition determines
whether that node is used in the conversation or to choose among the possible responses to the
user.
Conditions usually evaluate the intents and entities that are identified in the user responses, but
they can also evaluate information that is stored in the context.

© Copyright IBM Corp. 2018, 2019 11-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Responses
• The dialog response defines how to reply to the user.
• The dialog response consists of the messages that are based on the
identified intents, entities, or context that are communicated to the user
when the dialog node is activated.
• You can add variations
to the response for a
more natural experience.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-24. Watson Assistant components (cont.)

Responses
Responses are messages that are based on the identified intents and entities that are
communicated to the user when the dialog node is activated. You can add variations of the
response for a more natural experience, or add conditions to pick one response out of many in the
same dialog node.
The figure shows an example of adding different variations for greetings if the node is triggered by
a greeting intent from the user.

© Copyright IBM Corp. 2018, 2019 11-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant dialog features

Rich responses
• In addition to the default response type of text, you can return other
interactive response types to enhance the user experience.
• The following response types are supported:
ƒ Image: Embeds an image into the response.
ƒ Option: Adds a list of one or more options.
ƒ Pause: Forces the application to wait for a specified number of milliseconds before
continuing with processing.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-25. Watson Assistant dialog features

Rich responses
In addition to the default response type of text, you can return responses with multimedia or
interactive elements, such as images or clickable buttons to simplify the interaction model of your
application and enhance the user experience.
The following response types are supported:
• Image: Embeds an image into the response.
• Option: Adds a list of one or more options. When a user clicks one of the options, an associated
user input value is sent to the service. How options are rendered can differ depending on where
you deploy the dialog. For example, in one integration channel, the options might be displayed
as clickable buttons, but in another they might be displayed as a drop-down list.
• Pause: Forces the application to wait for a specified number of milliseconds before continuing
with processing. You can choose to show an indicator that the dialog is working on typing a
response. Use this response type if you need to perform an action that might take some time.

© Copyright IBM Corp. 2018, 2019 11-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant dialog features (cont.)

Multiple (conditional) responses
• In a single dialog node, you can provide different responses, each one
triggered by a different condition. Use this approach to address multiple
scenarios in a single node.
• Example: The service uses information that it collected earlier about the
user's location to tailor its response, and provide information about the
store nearest the user.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-26. Watson Assistant dialog features (cont.)

Multiple (conditional) responses

In a single dialog node, you can provide different responses, each one triggered by a different
condition. Use this approach to address multiple scenarios in a single node.
In this example, the service uses information that it collected earlier about the user's location to
tailor its response, and provide information about the store nearest the user. The conditional
responses are based on context values.
This single node now provides the equivalent function of four separate nodes.

© Copyright IBM Corp. 2018, 2019 11-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant dialog features (cont.)

Slots
• Add slots to a dialog node to gather multiple pieces of information from
a user within that node.
• Slots collect information at the user’s pace. Details that the user
provides are saved, and the service asks only for the details that the
user did not provide.
• Example: User-provided values for multiple slots in one input.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-27. Watson Assistant dialog features (cont.)

Slots
Add slots to a dialog node to gather multiple pieces of information from a user within that node.
Slots collect information at the users' pace. Details that the user provides are saved, and the
service asks only for the details the use did not provide.
Example:
The user wants to reserve a table in a restaurant. The needed information is the number of guests,
the date, the time, and the name of the restaurant. When asked, the user might provide values for
multiple slots at once. For example, the input might include the information, ”There will be 6 of us
dining at 7 PM”. This one input contains two of the missing required values: the number of guests
and time of the reservation. The service recognizes and stores both of them, each one in its
corresponding slot. It then displays the prompt that is associated with the next empty slot, which in
this case asks the user, “Where would you like to eat?” to determine the restaurant slot and stores
the response. After the user replies, the service asks, “What day will this take place?” to determine
the date slot, stores it, and gives a reply.
The following video provides a more detailed understanding of slots if you are interested:
https://console.bluemix.net/docs/services/assistant/dialog-slots.html#dialog-slots

© Copyright IBM Corp. 2018, 2019 11-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Dialog flow
• The dialog standard flow is processed from top to bottom and left to
right.
• Triggered by a successful condition.
• It ends when it reaches the last node in the branch that it is following.
User input

Match

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-28. Watson Assistant components (cont.)

Dialog flow
The dialog is processed by the service from top to bottom.
As it travels down the tree, if the service finds a condition that is met, it triggers that node. It then
moves from left to right on the triggered node to check the user input against any child node
conditions. As it checks the children nodes, it moves again from top to bottom.
The service continues to work its way through the dialog tree until it reaches the last node in the
branch that it is following.
If none of the conditions evaluates to true, then the response from the last node in the tree, which
typically has a special anything_else condition that always evaluates to true, is returned.
When you start to build the dialog, you must determine the branches to include and where to place
them. The order of the branches is important because nodes are evaluated from first to last. The
first node whose condition matches the input is used; any nodes that come later in the tree are not
triggered.

© Copyright IBM Corp. 2018, 2019 11-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Watson Assistant components (cont.)

Dialog depiction

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-29. Watson Assistant components (cont.)

Dialog depiction
This diagram shows a mockup of a dialog tree that is built with the GUI dialog builder tool. It
contains two root dialog nodes. A typical dialog tree would likely have many more nodes, but this
depiction provides a glimpse of what a subset of nodes might look like.
The first root node has conditions for an intent value. It has two child nodes and each have a
condition on an entity value. The second child node defines two responses. The first response is
returned to the user if the value of the context variable matches the value that is specified in the
condition. Otherwise, the second response is returned.
This standard type of node is useful to capture questions about a certain topic and then in the root
response ask a follow-up question that is addressed by the child nodes. For example, it might
recognize a user question about discounts and ask a follow-up question about whether the user is a
member of any associations with which the company has special discount arrangements. The child
nodes provide different responses based on the user's answer to the question about association
membership.

© Copyright IBM Corp. 2018, 2019 11-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty
The second root node is a node with slots. It also has conditions on an intent value. It defines a set
of slots, one for each piece of information that you want to collect from the user. Each slot asks a
question to elicit the answer from the user. It looks for a specific entity value in the user's reply to
the prompt, which it then saves in a slot context variable.
This type of node is useful for collecting details that you might need to perform a transaction on the
user's behalf. For example, if the user's intent is to book a flight, the slots can collect the origin and
destination location information, travel dates, and so on.

© Copyright IBM Corp. 2018, 2019 11-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty
11.3. Enriching the chatbot

© Copyright IBM Corp. 2018, 2019 11-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Enriching the chatbot

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-30. Enriching the chatbot

© Copyright IBM Corp. 2018, 2019 11-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Topics
• Chatbot components
• Watson Assistant components
• Enriching the chatbot

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-31. Topics

© Copyright IBM Corp. 2018, 2019 11-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Persona
• Creating a persona for your bot makes the bot friendlier and engages its
users.
• You can create a bot persona by adding some distinguishing
characteristics to your chatbot.
• Avatar: A face for your chatbot. A simple 2D graphic image, or even a
3D figure adds a nice touch, along with a name.
ƒ Adding a gender is not always a good idea. Generally, the chatbot should be
gender-neutral, such as a friendly android (robot) or a friendly pet like a cat
or a bird.

• A voice: Makes a chatbot more interactive and adds value to its

personality.
ƒ Easy to implement because of the many available text to speech services.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-32. Persona

Although it might be clear to the user that they are talking to a chatbot, creating a persona makes
the bot friendlier and engages its users. You can create a bot persona by providing some
distinguishing characteristics to your chatbot. For example, adding the following features can help
to accomplish this goal:
• Avatar
An avatar adds a face to your chatbot. A simple 2D graphic image adds a nice touch, along with
a name. Adding a gender is not always a good idea. Generally, the chatbot should be
gender-neutral, such as a friendly android (robot) or a friendly pet like a cat or a bird.
• A voice
Adding a voice to your chatbot makes it more interactive and adds value to its personality.
Doing so requires almost no effort because most text to speech services can be added to your
existing output response text to transform it into audio.

© Copyright IBM Corp. 2018, 2019 11-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Emotion and tone

• Sentiment analysis can map user emotion input to a positive,
negative, or neutral status.
ƒ Your chatbot can then sense the user’s positive comment and react to it, or
sense a negative input and direct the conversation appropriately.

• Tone analysis can perform more advanced interpretation of the user’s

mood.
ƒ For example, it can detect whether the user is frustrated or thankful. The
chatbot can then reply with a customized answer to each mood, giving your
bot emotional AI that adds to its personality and makes it friendlier.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-33. Emotion and tone

Emotion and tone

• Sentiment analysis can map user emotion input to a positive, negative, or neutral status. It
adds emotion to your chatbot. Your chatbot can sense the user’s positive comment and react to
it, or sense a negative input and direct the conversation appropriately.
• Tone analysis can perform more advanced interpretation of the user’s mood. For example, it
can detect whether the user is frustrated or thankful. The chatbot can then reply with a
customized answer to each mood, giving your bot emotional AI that adds to its personality and
makes it friendlier.

© Copyright IBM Corp. 2018, 2019 11-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Interfaces
• Using messaging platforms with your chatbot makes it more accessible
and user friendly.
• Most services and tools provide plug-ins or easy-to-use recipes to plug
your chatbot to these platforms.
• This approach simplifies the effort of designing a chat interface and
eliminates the need to download another app or registering on a
website to use the chatbot.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-34. Interfaces

Interfaces
One of the key factors in the rise of chatbots is the growing popularity of messaging apps. Using
messaging platforms with your chatbot makes it more accessible and friendly.
Most services and tools provide plug-ins or recipes to plug your chatbot to these platforms. This
approach simplifies the effort of designing a chat interface and eliminates the need to download
another app or registering on a website to use the chatbot.

© Copyright IBM Corp. 2018, 2019 11-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Speech recognition
• You can use IBM, Google, and Microsoft speech to text services to
enable your chatbot to understand user speech.
• This feature is heavily used in home automation chatbots and
automation tasks in general.
ƒ For example, in Microsoft Windows you can give commands to Cortana by
using your voice without touching a key or pressing a mouse button. You can
do the same with Siri on the Apple iPhone.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-35. Speech recognition

Speech Recognition
With advancements in speech to text technology, you can use IBM, Google, and Microsoft speech
to text services to enable your chatbot to understand user speech.
This feature is heavily used in home automation chatbots and automation tasks in general. For
example, in Microsoft Windows you can give commands to Cortana by using your voice without
touching a key or pressing a mouse button. You can do the same with Siri on the Apple iPhone.

© Copyright IBM Corp. 2018, 2019 11-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Unit summary
• Explain assistants and skills.
• Explain intents.
• Explain entities.
• Explain context variables.
• Describe how the nodes in a dialog are triggered.
• Describe how the dialog flow is processed.
• Describe the features that can be used to enrich the chatbot.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-36. Unit summary

© Copyright IBM Corp. 2018, 2019 11-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review questions
1. The ____ name is always prefixed with ’@’.
A. Intent
B. Entity
C. Dialog
D. Skill

2. True or False: The content catalog is used to add pre-built

entities.

3. Which feature of a dialog can be used to ask only for input

that the user has not already provided?
A. Rich response
B. Slot
C. Conditional response
D. Context variable

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-37. Review questions

1. B. Entity.
2. False. A content catalog that contains prebuilt common intents is provided with the Assistant
tool.
3. B. Slot.

© Copyright IBM Corp. 2018, 2019 11-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review questions (cont.)

4. Which of the following features can be used to enrich your
chatbot?
A. Avatar
B. Tone analysis
C. Speech recognition
D. Text to speech
E. All of the above
5. True or False: The dialog flow is from top to bottom and left
to right.
6. Which of the following response types can be used in a
dialog node?
A. Image
B. Text
C. Option
D. All the above
Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-38. Review questions (cont.)

4. E. All of the above.

5. True.
6. D. All the above.

© Copyright IBM Corp. 2018, 2019 11-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review questions (cont.)

7. #pay_bill is an example of ____
A. Intent
B. Entity
C. Skills
D. Workspace

8. A branching conversation flow that defines how your chatbot

responds when it recognizes the input from the user.
A. Intent
B. Dialog
C. Condition
D. Entity

9. True or False: @menu is an example of intent.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-39. Review questions (cont.)

7. A. Intent.
8. B. Dialog.
9. False. @menu is an example of entity.

© Copyright IBM Corp. 2018, 2019 11-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review answers
1. The ____ name is always prefixed with ’@’.
A. Intent
B. Entity
C. Dialog
D. Skill

2. True or False: The content catalog is used to add pre-built

entities.

3. Which feature of a dialog can be used to ask only for input

that the user has not already provided?
A. Rich response
B. Slot
C. Conditional response
D. Context variable

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-40. Review answers

1. B. Entity.
2. False. A content catalog that contains prebuilt common intents is provided with the Assistant
tool.
3. B. Slot.

© Copyright IBM Corp. 2018, 2019 11-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review answers (cont.)

4. Which of the following features can be used to enrich your
chatbot?
A. Avatar
B. Tone analysis
C. Speech recognition
D. Text to speech
E. All of the above
5. True or False: The dialog flow is from top to bottom and left
to right.
6. Which of the following response types can be used in a
dialog node?
A. Image
B. Text
C. Option
D. All the above
Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-41. Review answers (cont.)

4. E. All of the above.

5. True.
6. D. All the above.

© Copyright IBM Corp. 2018, 2019 11-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Review answers (cont.)

7. #pay_bill is an example of ____
A. Intent
B. Entity
C. Skills
D. Workspace
8. A branching conversation flow that defines how your chatbot
responds when it recognizes the input from the user.
A. Intent
B. Dialog
C. Condition
D. Entity
9. True or False: @menu is an example of intent.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-42. Review answers (cont.)

7. A. Intent.
8. B. Dialog.
9. False. @menu is an example of entity.

© Copyright IBM Corp. 2018, 2019 11-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Exercise: Getting started with

Watson Assistant.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-43. Exercise: Getting started with Watson Assistant.

© Copyright IBM Corp. 2018, 2019 11-49

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Exercise objectives
• This exercise introduces IBM Watson Assistant (formerly
Conversation) and walks you through the process of creating
a very simple chatbot with Watson Assistant.
• After completing this exercise you should be able to:
ƒ Create a Watson Assistant service instance.
ƒ Create a Watson Assistant skill.
ƒ Add intents.
ƒ Build a dialog.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-44. Exercise objectives

After completing this exercise you should be able to:

• Create a Watson Assistant service instance.
• Create a Watson Assistant skill.
• Add intents.
• Build a dialog.

© Copyright IBM Corp. 2018, 2019 11-50

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Exercise: Help Desk Chatbot

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-45. Exercise: Help Desk Chatbot

© Copyright IBM Corp. 2018, 2019 11-51

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 11. Introduction to IBM Watson Assistant

Uempty

Exercise objectives
• This exercise describes how to create a chatbot application
quickly without coding and integrate it with the Watson
Assistant service.
• After completing this exercise you should be able to:
ƒ Create a Watson Assistant skill.
ƒ Add intents and entities.
ƒ Build a dialog.
ƒ Create a Node-RED application that integrates with the Watson
Assistant service.
ƒ Set up Slack as a front-end chat service for the Help Desk chatbot.

Introduction to IBM Watson Assistant © Copyright IBM Corporation 2019

Figure 11-46. Exercise objectives

After completing this exercise you should be able to:

• Create a Watson Assistant skill.
• Add intents and entities.
• Build a dialog.
• Create a Node-RED application that integrates with the Watson Assistant service.
• Set up Slack as a front-end chat service for the Help Desk chatbot.

© Copyright IBM Corp. 2018, 2019 11-52

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Unit 12. Introduction to computer vision

Estimated time
00:30

Overview
This unit provides a high-level introduction to computer vision (CV).

© Copyright IBM Corp. 2018, 2019 12-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Unit objectives
• Define computer vision (CV).
• Know the history of CV and its advancement with artificial intelligence
(AI).
• Identify CV applications and use cases.
• List tools and services for CV.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 12-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

What is computer vision

• Computer vision is a branch of science that is concerned with
processing images to extract, analyze, and understand useful
information from a single image or image sequence.
• It aims at simulating the human visual system.
• It uses various machine learning and deep learning algorithms to
analyze images for scenes, objects, faces, and other content in videos,
photos, and pictures in general.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-2. What is computer vision

Computer vision is a branch of science that is concerned with processing images to extract,
analyze, and understand useful information from a single image or image sequence. It aims to
create an artificial (computer) system that can achieve the capabilities of a human visual system so
that the machine can “see”.
CV uses various machine learning algorithms to analyze images for scenes, objects, faces, and
other content in videos, photos, and pictures in general.
References:
http://www.bmva.org/visionoverview
https://console.bluemix.net/docs/services/visual-recognition/index.html#about

© Copyright IBM Corp. 2018, 2019 12-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision history

• Started with the emergence of AI In 1956.
• Convolutional neural networks were proposed in the well-known 1998
research paper by Yann LeCun and Léon Bottou.
ƒ 99.2% recognition accuracy on the MNIST data set.

https://commons.wikimedia.org/w/index.php?curid=64810040

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-3. Computer vision history

Started with the emergence of AI in 1956 and evolved with the advancements of AI.
Convolutional neural networks were proposed in the well-known 1998 research paper by Yann
LeCun and Léon Bottou. In their detailed paper, their proposed neural network architecture “LeNet
5” reached an accuracy of 99.2% on the Modified National Institute of Standards and Technology
(MINST) data set. The MINST data set is a large database of hand-written digits that is commonly
used for training various image processing systems. The database is also widely used for training
and testing in the field of machine learning.
Reference:
https://commons.wikimedia.org/w/index.php?curid=64810040

© Copyright IBM Corp. 2018, 2019 12-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision applications

• Manufacturing: Ensure that products are being positioned correctly on
an assembly line.
• Visual auditing: Look for visual compliance or deterioration in a fleet of
trucks, planes, windmills, transmission or power towers , and so on.
• Insurance: Classify claims images into different categories.
• Medical image processing: Detect tumors.
• Automotive industry: Object detection for safety.

Identifying skin cancer by

using CV

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-4. Computer vision applications

CV can be used in many applications and industries:

• Manufacturing: Use images from a manufacturing setting to make sure that products are being
positioned correctly on an assembly line, or ensure product quality by identifying defective parts
on the production line instead of by using manual validation.
• Visual auditing: Look for visual compliance or deterioration in a fleet of trucks, planes, or
windmills, etc.. in the field. Train custom models to understand what defects look like.
• Insurance: Rapidly process claims by using images to classify claims into different categories.
• Social listening: Use images from your product line or your logos to track buzz about your
company on social media.
• Medical image processing: Using images for diagnosing patients, such as the detection of
tumors.
• Automotive industry: There are many applications for CV in cars. For example, while parking
a car, a camera can detect objects and warn the driver when they get too close to them.
Reference:
https://www.research.ibm.com/artificial-intelligence/computer-vision/

© Copyright IBM Corp. 2018, 2019 12-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision applications (cont.)

• Social commerce: Use an image of a house to find similar homes that
are for sale.
• Social listening: Track the buzz about your company on social media
by looking for product logos.
• Retail: Use the photo of an item to find its price at different stores.
• Education: Use pictures to find educational material on similar
subjects.
• Public safety: Automated license-plate reading.

Company’s logo search

Introduction to computer vision

Interactive image search © Copyright IBM Corporation 2019

Figure 12-5. Computer vision applications (cont.)

Social commerce: Use an image of a house to find similar homes that are for sale.
Social listening: Use images from your product line or your logos to track buzz about your
company on social media.
Retail: Use the photo of an item to find its price at different stores.
Education: Use pictures to find educational material on similar subjects.
Public safety: Automated license-plate reading.
Do you know of or heard of any other applications?
Reference:
https://www.research.ibm.com/artificial-intelligence/computer-vision/

© Copyright IBM Corp. 2018, 2019 12-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision tasks

• Object detection and recognition: Detect certain patterns within the
image.
• Examples:
ƒ Detecting red eyes when taking photos in certain conditions.
ƒ Face recognition.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-6. Computer vision tasks

A CV task represents a well-defined problem in CV that can be solved to a certain extent or

accuracy by using one method or another.
Object detection and recognition deals with locating and detecting certain patterns within the
image. For example, detecting red eyes when taking photos in certain conditions. Other
applications include face detection and face recognition.
A CV task is also used in tracking objects, for example, tracking a ball during a football match,
tracking the movement of a cricket bat, or tracking a person in a video.
Reference:
https://www.ibm.com/watson/services/visual-recognition/demo/#demo

© Copyright IBM Corp. 2018, 2019 12-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision tasks (cont.)

• Content-based image retrieval: Image retrieval from a database
based on user’s image query.
ƒ By using image actual feature contents such as colors, shapes, and textures
ƒ Not using image metadata (keywords, tags, or descriptions)

• Optical character recognition (OCR): Converting hand-written text to

a digital format.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-7. Computer vision tasks (cont.)

Content-based image retrieval or “query-by image content” (QBIC) is the retrieval of images from
a database by using an image as a query. IBM was one of the pioneers in developing QBIC at the
IBM Almaden Research Center. "Content-based" refers to actual feature contents of the image like
colors, shapes, and textures. Other image retrieval systems rely on image metadata such as
keywords, tags, or descriptions that are associated with the image instead of image content.
Content-based image retrieval is preferred because searches that rely purely on metadata depend
on the quality of annotation.
Optical character recognition (OCR): Scan papers and hand-written forms, identify the
characters in them, and transform them into digital format (strings).
References:
http://www.ugmode.com/prior_art/lew2006cbm.pdf
https://en.wikipedia.org/wiki/Content-based_image_retrieval#cite_note-Survey-1

© Copyright IBM Corp. 2018, 2019 12-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision tasks (cont.)

• Object tracking: Following the position changes of a target object from
one frame to another in an image sequence or video.
• The following photo shows an example of human tracking.

(Sidenbladh, Black, and Fleet 2000) © 2000 Springer.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-8. Computer vision tasks (cont.)

Object tracking: Following the position changes of a target object from one frame to another within
an image sequence or video.
References:
https://en.wikipedia.org/wiki/Computer_vision
APA citation for image: Sidenbladh, H., Black, M. J., & Fleet, D. J. (2000, June). Stochastic tracking
of 3D human figures using 2D image motion. In European conference on computer vision (pp.
702-718). Springer, Berlin, Heidelberg.

© Copyright IBM Corp. 2018, 2019 12-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision tasks (cont.)

• Image restoration: Fixing and restoring images that are corrupted by
noise, such as motion blur, to their default state.
• Scene reconstruction: Creation of a 3D model by supplying the
system with multiple 2D images from different views. The computer
constructs a 3D model based on those images.

(Sinha, Steedly, Szeliskiet al. 2008) © 2008 ACM.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-9. Computer vision tasks (cont.)

Image restoration: Fixing and restoring images that are corrupted by noise, such as motion blur, to
their default state.
Scene reconstruction: Creation of 3D model by supplying the system with multiple 2D images
from different views. The computer constructs a 3D model based on those images.
References:
https://en.wikipedia.org/wiki/Computer_vision
APA image citation: Sinha, S. N., Steedly, D., Szeliski, R., Agrawala, M., & Pollefeys, M. (2008,
December). Interactive 3D architectural modeling from unordered photo collections. In ACM
Transactions on Graphics (TOG) (Vol. 27, No. 5, p. 159). ACM.

© Copyright IBM Corp. 2018, 2019 12-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision tools

• OpenCV: CV open-source library
ƒ C++, Python, Java, and MATLAB interfaces

• Microsoft Vision API: Specialized in OCR and analyzing videos

• IBM Watson Visual Recognition: A service on IBM Cloud
ƒ A set of built-in classes provides highly accurate results without training.
ƒ A trained custom model enables the use of the Visual Recognition service to
recognize images that are not available with pre-trained classification.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-10. Computer vision tools

OpenCV: An open-source library that can be used to perform most CV tasks that are required on
any language. It has C++, Python, Java, and MATLAB interfaces.
Microsoft Vision API: Specialized in OCR and analyzing videos.
IBM Watson Visual Recognition: This service is available on IBM Cloud. A set of built-in classes
provides highly accurate results without training.
You can train custom models to create specialized classes. With a custom model, you can train the
Visual Recognition service to classify images to suit your business needs. By creating a custom
model, you can use the Visual Recognition service to recognize images that are not available with
pre-trained classification.
Image reference:
https://www.ibm.com/blogs/bluemix/2017/05/watson-learns-see-food-introducing-watson-visual-rec
ognition-food-model/

© Copyright IBM Corp. 2018, 2019 12-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision use cases

• Facial recognition: We use facial recognition daily.
ƒ Taking a photo and applying effects by using your smartphone.
ƒ Tagging friends on social media.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-11. Computer vision use cases

Facial recognition is one of the most-used features of CV. It is often used in smartphones when you
take a photo or apply effects. Another widely used feature is tagging friends on social media. These
features use face recognition and facial identification, in which a face is recognized from the image
and identifies the person in the image. A facial recognition feature can recognize faces in an image,
as shown in the figure.
Image: https://www.ibm.com/blogs/bluemix/2016/02/openwhisk-and-watson-image-tagging-app/

© Copyright IBM Corp. 2018, 2019 12-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Computer vision use cases (cont.)

• Augmented reality: Manipulation and addition of a system-generated
image (3D or 2D) as an overlay of a user’s view.
• Examples: Google Glass, emoji filters in some mobile apps, and
Pokémon Go.
• Mobile shopping applications will give in-store shoppers instant product
details and promotions through their mobile devices.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-12. Computer vision use cases (cont.)

Augmented reality (AR) is the manipulation and addition of a system-generated image (3D or 2D)
as an overlay of a user’s view. Examples include Google Glass, emoji filters in some mobile apps,
and Pokémon Go.
While in-store shopping accounts for 92 percent of retail volume, consumers are expecting the
same levels of personalization and customization that they do when they shop online; 58 percent of
consumers want in-store product information and 19 percent of consumers are already browsing
their mobile devices while in-store. CV and AR technology can bring all the benefits of online
shopping into traditional shops. By creating augmented reality mobile shopping applications (apps),
as shown in figure, in-store shoppers immediately learn about product details and promotions
through their mobile devices.
For more information on AR, watch the following video:
https://youtu.be/EAVtHjzQnqY
Reference:
https://www.ibm.com/blogs/bluemix/2017/03/augmented-reality-new-horizon-multi-sensory-learnin
g/

© Copyright IBM Corp. 2018, 2019 12-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Unit summary
• Define computer vision (CV).
• Know the history of CV and its advancement with artificial intelligence
(AI).
• Identify CV applications and use cases.
• List tools and services for CV.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-13. Unit summary

© Copyright IBM Corp. 2018, 2019 12-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Review questions

1. One of the following items is NOT an application of CV:

A. Process claims by using images to classify claims into
different categories.

B. Real-time video stream analysis that includes targeted

observations, such as facial recognition and automated
license-plate reading.

C. Use images from a manufacturing setting to make sure that

products are being positioned correctly on an assembly line.

D. Sentiment analysis by analyzing the words that are posted in

social media channels.

2. True or False: Watson Visual Recognition cannot be trained.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-14. Review questions

1. D.
2. False. You can train custom models to create specialized classes.

© Copyright IBM Corp. 2018, 2019 12-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Review questions (cont.)

3. Which of the following items are CV tools and services?

(Select all that apply.)
A. Chatfuel.
B. API.ai.
C. OpenCV.
D. IBM Watson Visual Recognition.
E. C and D
F. All of the above
4. True or False: Convolutional neural networks were proposed
in the well-known 1998 research paper by Yann LeCun and
Léon Bottou.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-15. Review questions (cont.)

3. E. C and D.
4. True.

© Copyright IBM Corp. 2018, 2019 12-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Review answers

1. One of the following items is NOT an application of CV:

A. Process claims by using images to classify claims into
different categories.
B. Real-time video stream analysis to include targeted
observations, such as facial recognition and automated
license-plate reading.
C. Use images from a manufacturing setting to make sure that
products are being positioned correctly on an assembly line.
D. Sentiment analysis by analyzing the words that are posted in
social media channels.

2. True or False: Watson Visual Recognition cannot be trained.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-16. Review answers

1. D.
2. False. You can train custom models to create specialized classes.

© Copyright IBM Corp. 2018, 2019 12-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 12. Introduction to computer vision

Uempty

Review answers (cont.)

3. Which of the following items are CV tools and services?

(Select all that apply.)
A. Chatfuel.
B. API.ai.
C. OpenCV.
D. IBM Watson Visual Recognition.
E. C and D
F. All of the above
4. True or False: Convolutional neural networks were proposed
in the well-known 1998 research paper by Yann LeCun and
Léon Bottou.

Introduction to computer vision © Copyright IBM Corporation 2019

Figure 12-17. Review answers (cont.)

3. E. C and D.
4. True.

© Copyright IBM Corp. 2018, 2019 12-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Unit 13. Computer vision fundamentals

Estimated time
00:30

Overview
This unit explains the basic steps of a typical computer vision (CV) pipeline, how CV analyzes and
processes images, and explores commonly used techniques in CV.

© Copyright IBM Corp. 2018, 2019 13-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Unit objectives
• Describe image representation for computers.
• Describe the computer vision (CV) pipeline.
• Describe different preprocessing techniques.
• Explain image segmentation.
• Explain feature extraction and selection.
• Describe when object recognition takes place.

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 13-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty
13.1. Image representation

© Copyright IBM Corp. 2018, 2019 13-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Image representation

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-2. Image representation

© Copyright IBM Corp. 2018, 2019 13-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Topics
• Image representation
• Computer vision pipeline

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-3. Topics

© Copyright IBM Corp. 2018, 2019 13-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Image representation
• Images are stored as a 2D array of pixels on computers.
• Each pixel has a certain value representing its intensity.
• Example of grayscale representation:
í Image is black and white with shades of gray in between.
í Pixel intensity is a number between 0 (black) and 255 (white).

int[ ][ ] array = { {255, 170, 170, 0},

{220, 80, 80, 170},
{255, 80, 0, 0},
{175, 20, 170, 0} };

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-4. Image representation

It is important to understand how images are stored and represented on computer screens. Images
are made of grids of pixels, that is, a two-dimensional (2D) array of pixels, where each pixel has a
certain value representing its intensity. A pixel represents a square of color on the user’s screen.
There are many ways to represent color in images.
If the image is grayscale, that is, black and white with shades of gray in between, the intensity is a
number in the range 0 - 255, where 0 represents black and 255 represents white. The numbers in
between these two values are different intensities of gray.
For example, in the picture in the slide, assume that you selected a small square from the image
(the part in the red square). The pixel representation for it is in black, white, and shades of gray. To
the right of the picture is the numeric values of these pixels in a 2D array.

Note

The 256 scaling is a result of using 8-bit storage (28 =256).

© Copyright IBM Corp. 2018, 2019 13-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty
References:
http://www.csfieldguide.org.nz/en/chapters/data-representation.html
https://www.sqa.org.uk/e-learning/BitVect01CD/page_36.htm
https://www.mathworks.com/help/examples/images/win64/SegmentGrayscaleImageUsingKMeans
ClusteringExample_01.png

© Copyright IBM Corp. 2018, 2019 13-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Image representation (cont.)

ƒ Example of color representation:
í The pixel color is represented as a mix of Red, Green, and Blue.
í The pixel intensity becomes three 2D arrays or one 2D array, where each entry is
an object containing the 3 color values of RGB

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-5. Image representation (cont.)

If the image is colored, there are many color models that are available. The most well-known model
is RGB, where the color of the pixels is represented as a mix of Red, Blue, and Green color
channels. The value of the pixel intensity is represented as three 2D arrays that represent the three
color channels, where each color value is in the range 0 – 255. The color value represents different
intensities of the colors and all the colors that you see on the screen. The number of color
variations that are available in RGB is 256 * 256 *256 = 16,777,216 possible colors.
Depending on the data structure used that image appears as
• Three 2D arrays, with each 2D array representing the values and intensities for one color. The
image is a combination of all three arrays.
• One 2D array, where each entry in the array is an object containing the 3 color values of RGB
References:
http://www.csfieldguide.org.nz/en/chapters/data-representation.html
https://www.sqa.org.uk/e-learning/BitVect01CD/page_36.htm
https://www.mathworks.com/company/newsletters/articles/how-matlab-represents-pixel-colors.html

© Copyright IBM Corp. 2018, 2019 13-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty
13.2. Computer vision pipeline

© Copyright IBM Corp. 2018, 2019 13-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-6. Computer vision pipeline

© Copyright IBM Corp. 2018, 2019 13-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Topics
• Image representation
• Computer vision pipeline

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-7. Topics

© Copyright IBM Corp. 2018, 2019 13-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline

• The steps and functions that are included are highly dependent on the
application.
• Here is a conventional visual pattern recognition pipeline.

Feature
Image Pre- High-level
Segmentation Extraction &
Acquisition Processing Processing
Selection

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-8. Computer vision pipeline

The steps and functions that are included in a CV system algorithm pipeline are highly dependent
on the application. The application might be implemented as a stand-alone part of a system and
might apply to only a certain step of the pipeline, or it can be a larger application, that is, an
end-to-end application that takes certain images and then applies all of the steps and functions in
the pipeline.
Reference:
https://www.researchgate.net/publication/273596152_Hardware_Architecture_for_Real-Time_Com
putation_of_Image_Component_Feature_Descriptors_on_a_FPGA

© Copyright IBM Corp. 2018, 2019 13-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

1. Image acquisition:
• The process of acquiring images and saving them in a digital image
format for processing.
• Images often use common formats, such as .jpeg, .png, and .bmp.
• Images are 2D images that are stored as arrays of pixels according to
their color model.

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-9. Computer vision pipeline (cont.)

1. Image acquisition
Image acquisition is the process of acquiring images and saving them in a digital image format for
processing in the pipeline.
Images are acquired from image sensors, such as commercial cameras. There are other types of
light-sensitive devices that can capture different types of images. Other image sensors include
radar, which uses radio waves for imaging.
Depending on the type of the device, the captured image can be 2D, 3D, or a sequence of images.
These images often use common formats, such as .jpeg, .png, and .bmp.
Images are stored as arrays of pixels according to their color model.
Reference:
https://en.wikipedia.org/wiki/Computer_vision#System_methods

© Copyright IBM Corp. 2018, 2019 13-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

2. Pre-processing:
• Preparing the image for the processing stage
• Examples:
ƒ Resizing images
ƒ Noise reduction
ƒ Contrast adjustment

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-10. Computer vision pipeline (cont.)

2. Pre-processing:
This stage focuses on preparing the image for the processing stage.
Examples:
• Images are resized as a form of normalization so that all images are the same size.
• Noise reduction reduces noise that represents false information in the image, as shown in the
slide.
Image citation: A Spatial and Frequency Domain Analysis of the Effect of Removal Attacks on
Digital Image Watermarksǁ - Scientific Figure on ResearchGate. Available from:
https://www.researchgate.net/Effect-of-adding-salt-pepper-noise-to-an-image-a-Original-water
marked-image-b-Salt_fig3_229008840 [accessed 18 Nov, 2018]
• Contrast adjustment helps with the detection of image information. In the images of the little girl,
each image represents a different contrast adjustment.
Image source: https://www.mathworks.com/help/images/contrast-adjustment.html
References:
https://en.wikipedia.org/wiki/Computer_vision#System_methods

© Copyright IBM Corp. 2018, 2019 13-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

3. Segmentation:
• Partitioning an image into regions of similarity.
• Grouping pixels and features with similar characteristics together.
• Helps with selecting regions of interest within the images. These
regions can contain objects of interest that we want to capture.
• Segmenting an image into foreground
and background.

(Cremers, Rousson, and Deriche 2007) © 2007 Springer

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-11. Computer vision pipeline (cont.)

3. Segmentation
The position of the image segmentation phase is not fixed in the CV pipeline. It might be a part of
the pre-processing phase or follow it (as in our pipeline) or be part of the feature extraction and
selection phase or follow them.
Segmentation is one of the oldest problems in CV and has the following aspects:
• Partitioning an image into regions of similarity.
• Grouping pixels and features with similar characteristics together.
• Helps with selecting regions of interest within the images. These regions can contain objects of
interest that we want to capture.
• Segmenting an image into foreground and background to apply further processing on the
foreground.

© Copyright IBM Corp. 2018, 2019 13-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty
Image citation: Cremers, D., Rousson, M., & Deriche, R. (2007). A review of statistical approaches
to level set segmentation: integrating color, texture, motion and shape. International journal of
computer vision, 72(2), 195-215.
References:
https://en.wikipedia.org/wiki/Computer_vision
http://szeliski.org/Book/drafts/SzeliskiBook_20100903_draft.pdf
http://www.cse.iitm.ac.in/~vplab/courses/CV_DIP/PDF/lect-Segmen.pdf

© Copyright IBM Corp. 2018, 2019 13-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

4. Feature extraction and selection:
• Image features are extracted.
• Image features examples:
ƒ Lines and edges
ƒ Corners

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-12. Computer vision pipeline (cont.)

4. Feature extraction and selection

Image features are extracted from the image. Typical examples of such features are:
• Lines and edges: These features are where sharp changes in brightness occur. They represent
the boundaries of objects.
• Corners: These features are points of interest in the image where intersections or changes in
brightness happens.
These corners and edges represent points and regions of interest in the image.
Brightness in this context refers to changes the in pixel intensity value.
References:
https://en.wikipedia.org/wiki/Feature_detection_(computer_vision)
https://www.mathworks.com/discovery/edge-detection.html
https://en.wikipedia.org/wiki/Computer_vision
Image reference: https://www.mathworks.com/discovery/edge-detection.html

© Copyright IBM Corp. 2018, 2019 13-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

• Some extracted features might be irrelevant or redundant.
• After feature extraction comes feature selection.
• Feature selection is choosing a feature subset that can reduce
dimensionality with the least amount of information loss.

All Features Selection Selected

Techniques Features

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-13. Computer vision pipeline (cont.)

For feature extraction, all the features in the image that could be extracted are present. Now, we
start selecting the features that are of interest. Some extracted features maybe irrelevant or
redundant.
Here are some reasons to perform feature selection:
• Reduce the dimensions of the features that were extracted from the image.
• Avoid overfitting when training the model with the features.
• Create simpler models with less training time.
References:
https://en.wikipedia.org/wiki/Feature_selection
https://www.nature.com/articles/srep10312

© Copyright IBM Corp. 2018, 2019 13-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

5. High-level processing:
• More processing is done on the segmented images to identify more
features from the image.
• Example: After segmentation to partition a face region, identify features
on the face, such as hair style, age, and gender.

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-14. Computer vision pipeline (cont.)

5. High-level processing:
In high-level processing, further processing is done on the segmented images to identify more
features from the image. For example, after the image is segmented to partition the face region,
identify features on the face such as hair style, age, and gender.
In this step, object recognition or classification takes place.

© Copyright IBM Corp. 2018, 2019 13-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Computer vision pipeline (cont.)

6. Decision making:
• Apply logic to make decisions based on detected images.
• Examples:
ƒ Security application: Grant access based on face recognition.
ƒ In a greenhouse environment, a notification is sent to the engineers to act if a
plant is detected as suffering from decay.

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-15. Computer vision pipeline (cont.)

6. Decision making
In this stage, after getting the output from the CV pipeline, users can apply logic that is based on
the findings to make decisions based on detected images.
For example, in security applications, the system can decide to grant access to a person if a face
that is detected is identified as the owner of a facility.
Another example is in a greenhouse environment, where a notification is sent to the engineers to
act if a plant is detected as suffering from decay.

© Copyright IBM Corp. 2018, 2019 13-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Unit summary
• Describe image representation for computers.
• Describe the computer vision (CV) pipeline.
• Describe different preprocessing techniques.
• Explain image segmentation.
• Explain feature extraction and selection.
• Describe when object recognition takes place.

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-16. Unit summary

© Copyright IBM Corp. 2018, 2019 13-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Review questions
1. True or False: There is only one model to represent color in
images, which is the RGB color model.
2. Which function is not part of the pre-processing stage?
A. Resizing images
B. Corner detection
C. Contrast adjustment
D. Noise reduction
3. True or False: In a CV pipeline, high-level processing deals with
detecting different segments of the image that can be subject of
analysis, like face detection.
4. Which of the following items is an example of feature extraction:
A. Size
B. Color
C. Lines and edges
D. Noise

Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-17. Review questions

1. False.
2. B.
3. False. In high-level processing, further processing is done on the segmented images to identify
more features from the image. For example, after the area of a face is partitioned during image
segmentation, features of the face such as the nose are identified by high level processing.
4. C. Lines and edges.

© Copyright IBM Corp. 2018, 2019 13-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 13. Computer vision fundamentals

Uempty

Review answers
1. True or False: There is only one model to represent color in
images, which is the RGB color model.

2. Which function is not part of the pre-processing stage?

A. Resizing Images
B. Corner detection
C. Contrast adjustment
D. Noise reduction
3. True or False: In the CV pipeline, high-level processing deals
with detecting different segments of the image that can be
subject of analysis, like face detection.
The answer is False.
4. Which of the following items is an example of feature extraction:
A. Size
B. Color
C. Lines and edges
D. Noise
Computer vision fundamentals © Copyright IBM Corporation 2019

Figure 13-18. Review answers

1. False.
2. B. Corner detection.
3. False. In high-level processing, further processing is done on the segmented images to identify
more features from the image. For example, after the area of a face is partitioned during image
segmentation, features of the face such as the nose are identified by high level processing.
4. C. Lines and edges.

© Copyright IBM Corp. 2018, 2019 13-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Unit 14. Introduction to IBM Watson

Visual Recognition
Estimated time
00:45

Overview
This unit introduces the IBM Watson Visual Recognition service, describes its capabilities, and how
to train the service.

© Copyright IBM Corp. 2018, 2019 14-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Unit objectives
• List the features that are available with IBM Watson Visual Recognition.
• List the built-in models.
• Explain the capabilities of the built-in models.
• Explain the difference between the built-in and custom models.
• Describe how to train a custom model.
• Describe how to update a custom model.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 14-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty
14.1. Watson Visual Recognition overview

© Copyright IBM Corp. 2018, 2019 14-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Watson Visual Recognition

overview

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-2. Watson Visual Recognition overview

© Copyright IBM Corp. 2018, 2019 14-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Topics
• Watson Visual Recognition overview
• Visual Recognition built-in models
• Custom models

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-3. Topics

© Copyright IBM Corp. 2018, 2019 14-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Watson Visual Recognition service

• Uses deep learning algorithms to analyze images for scenes, objects,
faces, food, and other content.
• The analysis response includes keywords that provide information
about the content.
• A set of built-in classes provides highly accurate results without training.
• Can be trained to create custom models to classify images to suit
specific business needs.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-4. Watson Visual Recognition service

The Watson Visual Recognition service uses deep learning algorithms to analyze images for
scenes, objects, faces, food, and other content. The services response includes keywords that
provide information about the content. A set of built-in classes provides highly accurate results
without training.
You can train custom models to create specialized classes. With a custom model, you can train the
Visual Recognition service to classify images to suit your business needs. By creating a custom
model, you can use the Visual Recognition service to recognize images that are not available with
pre-trained classification.

© Copyright IBM Corp. 2018, 2019 14-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Watson Visual Recognition service (cont.)

The following image shows the process of creating and using Watson
Visual Recognition.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-5. Watson Visual Recognition service (cont.)

For built-in models, gather only the images that you want to analyze, send them to the built-in
models, and then view the results. As shown in the graphic in this slide, the process starts from the
top in “Prepare images.”, followed by “Analyze images.”, and then “View results.”
For custom models, first train your own custom model with your own training data. When the model
is trained and ready, send the images that you want to analyze to the model, and then view the
results. As shown in the graphic in this slide, the process starts from the bottom in “Prepare training
data.”, followed by “Train and create new models.”, then “Analyze images.”, and then “View results.”

© Copyright IBM Corp. 2018, 2019 14-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty
14.2. Visual Recognition built-in models

© Copyright IBM Corp. 2018, 2019 14-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition built-in

models

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-6. Visual Recognition built-in models

© Copyright IBM Corp. 2018, 2019 14-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Topics
• Watson Visual Recognition overview
• Visual Recognition built-in models
• Custom models

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-7. Topics

© Copyright IBM Corp. 2018, 2019 14-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition built-in models

• Built-in models that are available:
ƒ General model
ƒ Face model
ƒ Explicit model
ƒ Food model
ƒ Text model (private beta)

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-8. Visual Recognition built-in models

A set of built-in models provides highly accurate results without training:

General model: Default classification from thousands of classes.
Face model: Facial analysis with age and gender.
Explicit model: Assess whether an image contains objectionable or adult content that might be
unsuitable for general audiences.
Food model: Specifically for images of food items.
Text model (Private beta): Text extraction from natural scene images. The text model is not
available for public use because it is still in beta.
We describe the General model, Face model, and Food model in the following slides.
Reference:
https://console.bluemix.net/docs/services/visual-recognition/index.html#models

© Copyright IBM Corp. 2018, 2019 14-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition General model

• The General model returns classes from thousands of possible tags
that are organized into categories and subcategories.
• Top-level categories:
ƒ Animals (including birds, reptiles, amphibians, and others)

ƒ Person and people-oriented information and activities

ƒ Food (including cooked food and beverages)

ƒ Plants (including trees, shrubs, aquatic plants, and vegetables)

ƒ Sports

ƒ Nature (including many types of natural formations and geological structures)

ƒ Transportation (land, water, and air)

ƒ Others, including furnishings, musical instruments, tools, colors, gadgets,

devices, instruments, weapons, and buildings
Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-9. Visual Recognition General model

The General model returns classes from thousands of possible tags that are organized into
categories and subcategories. The following list shows the top-level categories:
• Animals (including birds, reptiles, amphibians, and others)
• Person and people-oriented information and activities
• Food (including cooked food and beverages)
• Plants (including trees, shrubs, aquatic plants, and vegetables)
• Sports
• Nature (including many types of natural formations and geological structures)
• Transportation (land, water, and air)
• Others, including furnishings, fruits, musical instruments, tools, colors, gadgets, devices,
instruments, weapons, buildings, structures and manufactured objects, clothing and garments,
and flowers.
Reference:
https://console.bluemix.net/docs/services/visual-recognition/customizing.html#general-model

© Copyright IBM Corp. 2018, 2019 14-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition General model (cont.)

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-10. Visual Recognition General model (cont.)

General model
The General model in the Watson Visual Recognition service analyses the image, classifies the
image and the objects that it includes, and then returns the results with the associated confidence
score.

© Copyright IBM Corp. 2018, 2019 14-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition Face model

The Face model detects human faces in the image, and provides an
estimated age range and gender.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-11. Visual Recognition Face model

Face model
This model detects human faces in images. This slide shows an example for face detection that
uses the Watson Visual Recognition Face model. The response that is returned from the model
provides the location of the face in the image, which here is shown as a bounding box. This service
also provides a general indication of the age range and gender of faces.

© Copyright IBM Corp. 2018, 2019 14-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Visual Recognition Food model

The Food model uses a specialized vocabulary to identify food items with
enhanced accuracy.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-12. Visual Recognition Food model

Food model
The Food model uses a specialized vocabulary of over 2,000 foods to identify meals, food items,
and dishes with enhanced accuracy. The Food model recognizes more food and meals than the
general (default) model.

© Copyright IBM Corp. 2018, 2019 14-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty
14.3. Custom models

© Copyright IBM Corp. 2018, 2019 14-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom models

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-13. Custom models

© Copyright IBM Corp. 2018, 2019 14-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Topics
• Watson Visual Recognition overview
• Visual Recognition built-in models
• Custom models

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-14. Topics

© Copyright IBM Corp. 2018, 2019 14-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model training

• A custom model enables you to train the Visual Recognition service to
classify images to suit your business needs.
• A custom model is a group of classes that are trained against each
other.
• During training, classes are created when you upload separate
compressed (.zip) files of positive examples for each class.
ƒ For example, to create a classifier that is called "fruit", you might upload a
compressed file of images of pears, a compressed file of images of apples,
and a compressed file of images of bananas in a single training call.

• You can also provide a compressed file of negative examples in the

same training call to further improve your classifier.
ƒ For example, for the custom classifier “fruit”, you might provide a
compressed file with images of various vegetables.

• You must provide at least two example .zip files: two positive examples
files or one positive and one negative file.
Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-15. Custom model training

Although the General model is enhanced frequently, you might still need to create your own custom
model for a specific case.
A custom model (also known as custom classifier) is a group of classes that are trained against
each other to create a multi-faceted classifier that can identify highly specialized subjects and
provide a score for individual classes.
During training, classes are created when you upload separate compressed (.zip) files of positive
examples for each class. For example, to create a classifier that is called "fruit", you might upload a
compressed file of images of pears, a compressed file of images of apples, and a compressed file
of images of bananas in a single training call.
You can also provide a compressed file of negative examples in the same training call to further
hone your classifier. Negative example files are not used to create a class. For example, for the
custom classifier “fruit”, you might provide a compressed file with images of various vegetables.

Important

You must provide at least two example .zip files: two positive examples files or one positive and one
negative file.

© Copyright IBM Corp. 2018, 2019 14-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model training (cont.)

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-16. Custom model training (cont.)

Structure of the training data. Each class that represents a certain fruit has a separate compressed
file, which contains the positive examples for the model training. A separate compressed file for
negative examples can also be provided to further hone your classifier. Negative example files are
not used to create a class. For the custom classifier "fruit", you might provide a .zip file with images
of various vegetables.

© Copyright IBM Corp. 2018, 2019 14-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model training (cont.)

• The system trains three models for each set: Apples, Bananas, and
Pears.
• For the Apples model, the group of pictures in “Apples” is trained as a
positive example, and the other groups are trained as negative
examples.
• If an image is duplicated in both the negative and positive sets, the rule
is that a duplicate image is kept in the positive set.
• After training completes, the model returns the classifier “fruit” as an
array that includes the classes “pears”, “apples”, and “bananas” with
their respective confidence scores.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-17. Custom model training (cont.)

If you train a classifier with three sets of positive class pictures, such as Apples, Bananas, and
Pears, the system trains three models internally.
For the Apples model, the group of pictures in “Apples” is trained as a positive example, and the
other groups are trained as negative examples. The system then knows that bananas and pears
are not apples. The other classes are used as negative examples for the Bananas and Pears
models as well.
If an image is duplicated in both the negative and positive sets, the rule is that a duplicate image is
kept in the positive set. After training completes, when the service identifies fruit in an image, it
returns the classifier “fruit” as an array that includes the classes “pears”, “apples”, and “bananas”
with their respective confidence scores.

© Copyright IBM Corp. 2018, 2019 14-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Training images examples

Training images:

Testing image:

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-18. Training images examples

Good example of training and testing images: The following images were used for training and
testing by OmniEarth, an environmental technology company. These images are good for training
because images in the training and testing sets should resemble each other with regard to angle,
lighting, distance, size of subject, and other factors.
Reference:
https://www.ibm.com/blogs/bluemix/2016/10/watson-visual-recognition-training-best-practices/

© Copyright IBM Corp. 2018, 2019 14-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Training images examples (cont.)

Training image:

Testing image:

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-19. Training images examples (cont.)

Bad example of training and testing images: The following images demonstrate bad training
because the training image shows a close-up shot of a single apple while the testing image shows
a large group of apples taken from a distance with other visual items introduced (baskets, sign, and
other items). It is possible that Watson might fail to classify the test image as ‘apples,’ especially if
another class in the classifier contains training images of a large group of round objects (such as
peaches, oranges, or other objects).
Try to have your training images from the setting in which your application runs and that are similar
to the test images.
Reference:
https://www.ibm.com/blogs/bluemix/2016/10/watson-visual-recognition-training-best-practices/

© Copyright IBM Corp. 2018, 2019 14-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Updating custom models

• You can update an existing custom model by adding new classes or by
adding new images to existing classes.
• You must supply at least one compressed file with more positive or
negative examples.
• Compressed files that contain positive examples are used to create and
update “classes” to affect all of the classes in that classifier.
• The prefix that you specify for each positive example parameter is used
as the class name within the new classifier. The “_positive_examples”
suffix is required.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-20. Updating custom models

You can update a classifier by adding new classes or by adding new images to existing classes.
You must supply at least one compressed file with more positive or negative examples.
Compressed files that contain positive examples are used to create and update “classes” to affect
all of the classes in that classifier.
The prefix that you specify for each positive example parameter is used as the class name within
the new classifier. The “_positive_examples” suffix is required.

© Copyright IBM Corp. 2018, 2019 14-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Updating custom models (cont.)

• Negative examples are not used to create a class within the created
classifier, but they define what the updated classifier is not.
• Negative example files must contain images that do not represent the
subject of any of the positive examples.
• The custom model uses binary “one versus the rest” models to train
each class against the other classes.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-21. Updating custom models (cont.)

Negative examples are not used to create a class within the created classifier, but they define what
the updated classifier is not.
Negative example files must contain images that do not represent the subject of any of the positive
examples.
The custom model uses binary “one versus the rest” models to train each class against the other
classes.

© Copyright IBM Corp. 2018, 2019 14-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Updating custom models (cont.)

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-22. Updating custom models (cont.)

The figure shows updating a classifier by adding new classes (oranges), by adding new images to
existing classes (apples) and by adding new negative examples (cheese).
Let us assume you want to retrain your classifier with new positive classes: YellowPears and
GreenPears. In order to do this, you'll need to manually look through your old pears.zip folder, and
split the images out into two new folders: YellowPears.zip and GreenPears.zip.
For example, when creating YellowPears or GreenPears, every single yellow pear image from the
original pears.zip training set should be exactly copied into the YellowPears.zip folder; otherwise,
any image that is not copied exactly will be in the Pears training set, and used as a negative when
YellowPears is trained.
Now, you simply retrain the system with YellowPears.zip and GreenPears.zip as positive examples.
When you do this, the system recognizes the exact duplicate images in the YellowPears and
GreenPears folders from the original pears.zip folder, and those images are retrained as positive
examples for their new classes. The rule is that a duplicate image is kept in the positive set, if it is
also found in both the negative and positive set for a class.

© Copyright IBM Corp. 2018, 2019 14-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model scores

• The classify method produces a score in the range of 0.0 - 1.0 for each
image for each class.
• How do you use the scores?
ƒ Think about the possible actions to take in response to a classification.

ƒ Understand the final application to determine the “decision threshold”.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-23. Custom model scores

The classify method produces a score in the range of 0.0 - 1.0 for each image for each class.
The scores for custom classifiers are not comparable to the scores that are returned by the General
built-in classifier.
How do you use the scores?
• Think about possible actions to take in response to a classification.
• This cost-benefit balance is crucial to deciding what to do with each class score, and only a
user who understands the final application can determine it. The score value that is needed for
the application to act is called the decision threshold. The service does not compute this value
for you.

© Copyright IBM Corp. 2018, 2019 14-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model - Example

• Objective: Classify the status of your car parking spot.
• Possible statuses:
ƒ Your car is in the spot.
ƒ Some other car is in the spot.
ƒ The spot is empty.
ƒ The camera is blocked.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-24. Custom model - Example

Assume that you have a webcam that is monitoring a parking space. The objective is to classify the
status of your car parking spot. You have the following possible statuses:
• Your car is in the spot.
• Some other car is in the spot.
• The spot is empty.
• The camera is blocked.

© Copyright IBM Corp. 2018, 2019 14-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model – Example (cont.)

• You collect training examples for each of these cases and train a
custom model with four classes.
• Your application classifies images from the webcam to report the status
of the spot, and the system notifies you with a message if the status is
unexpected.
• When the service classifies the image from the camera, it produces four
scores: myCar, unknownCar, emptySpot, and blockedCamera.
• The first action to consider is whether to send a notification.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-25. Custom model – Example (cont.)

You collect pictures as training examples for each of these cases and train a custom classifier with
four classes.
Your application classifies images from the webcam to report the status of the spot, and the system
notifies you with a message if the status is unexpected. When the service classifies the image from
the camera, it produces four scores: myCar, unknownCar, emptySpot, and blockedCamera.
Now, based on this use case, the first action might be to send a notification about the parking
status.

© Copyright IBM Corp. 2018, 2019 14-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Custom model – Example (cont.)

• Suppose that you write your code to send a notification if the myCar
score is less than 0.75, or if one of the other scores is greater than 0.6.
• During the day, there is one false alarm every three hours:
ƒ Reason: People walk by and obscure the car.
ƒ Accepting these alarms at night is annoying.

• The notification logic and threshold likely vary depending on:

ƒ The perceived risk of car theft.
ƒ The accuracy of your model.
ƒ The amount of annoyance that is caused by a false alarm.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-26. Custom model – Example (cont.)

Suppose you park in your spot and have the service start classifying the images. You see that the
myCar score is computed as 0.8 on average over a few hours, the unknownCar score hovers
around 0.3, emptySpot is around 0.15, and blockedCamera is around 0.1. Using this data, you write
your code to notify you if the myCar score is less than 0.75, or if one of the other scores is greater
than 0.6.
During the day, you receive approximately one false alarm every three hours when people walk by
and obscure the car. The system sends you the photo along with the notice so that you can see that
an issue does not exist. This approach works, but at night those false alarms every three hours
become annoying. Your preferences for day versus night notification reflect the higher cost of a
false alarm at night time for your application.
Therefore, the notification logic and threshold likely vary, depending on the perceived risk of car
theft, the accuracy of your classifiers, and the amount of annoyance that is caused by a false alarm.
Similarly, as a person, you might face the same tradeoff. If the system notifies you that the camera
was blocked, the accompanying image likely is all black or gray. Do you go to check on the car in
person or ignore it? Your decision depends on your other priorities and the perceived risks.

© Copyright IBM Corp. 2018, 2019 14-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Unit summary
• List the features that are available with IBM Watson Visual Recognition.
• List the built-in models.
• Explain the capabilities of the built-in models.
• Explain the difference between the built-in and custom models.
• Describe how to train a custom model.
• Describe how to update a custom model.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-27. Unit summary

© Copyright IBM Corp. 2018, 2019 14-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Review questions
1. True or False: By using the Watson Visual Recognition
service, you can create your own custom model.

2. What is the highest confidence value that is presented by

the Watson Visual Recognition model?
A. 100.
B. 0.9.
C. 1.
D. 10.

3. To use the Watson Visual Recognition service, the first thing

that you do is:
A. Create your own custom model.
B. Create a Watson Visual Recognition service instance.
C. Use the General model to detect faces.
D. Use the custom model to detect faces.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-28. Review questions

1. True.
2. C. The answer is 1.
3. B.

© Copyright IBM Corp. 2018, 2019 14-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Review questions (cont.)

4. True or False: The Watson Visual Recognition service must
be trained before it can be used.

5. To train a custom model (classifier) you must provide at

least:
A. One positive example.
B. One negative example.
C. Two positive examples or one positive example and one
negative example.
D. Two positive examples and two negative examples.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-29. Review questions (cont.)

4. False. Visual Recognition includes a set of built-in models that provides highly accurate results
without training.
5. C. At least two example .zip files must be provided: Two positive examples or one positive
example and one negative example.

© Copyright IBM Corp. 2018, 2019 14-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Review answers
1. True or False: By using the Watson Visual Recognition
service, you can create your own custom classifier.

2. What is the highest confidence value that is presented by

Watson Visual Recognition Classifier?
A. 100.
B. 0.9.
C. 1.
D. 10.
3. To use the Watson Visual Recognition service, the first thing
that you must do is:
A. Create your own custom classifier.
B. Create a Watson Visual Recognition service instance.
C. Use the default classifier to detect faces.
D. Use the custom classifier to detect faces.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-30. Review answers

1. True.
2. C. The answer is 1.
3. B.

© Copyright IBM Corp. 2018, 2019 14-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Review answers (cont.)

4. True or False: The Watson Visual Recognition service must
be trained before it can be used.

5. To train a custom model (classifier) you must provide at

least:
A. One positive example.
B. One negative example.
C. Two positive examples or one positive example and one
negative example.
D. Two positive examples and two negative examples.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-31. Review answers (cont.)

Write your answers here:

4. False. Visual Recognition includes a set of built-in models that provides highly accurate results
without training.
5. C. At least two example .zip files must be provided: Two positive examples or one positive
example and one negative example.

© Copyright IBM Corp. 2018, 2019 14-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Exercise: Classifying images

with Watson Visual
Recognition

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-32. Exercise: Classifying images with Watson Visual Recognition

© Copyright IBM Corp. 2018, 2019 14-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 14. Introduction to IBM Watson Visual Recognition

Uempty

Exercise objectives
• This exercise guides you through using the default models in
IBM Watson Visual Recognition to classify an image, detect
faces, and recognize text in an image.
• After you learn how to classify an image by using the default
General model, you will learn to create and train a custom
model.
• After completing this exercise you should be able to:
ƒ Create a Watson Visual Recognition service and obtain the API
key value.
ƒ Use Visual Recognition API methods to:
í Classify images
í Detect faces in an image
í Recognize text in an image
ƒ Create and train a custom model.

Introduction to IBM Watson Visual Recognition © Copyright IBM Corporation 2019

Figure 14-33. Exercise objectives

After completing this exercise you should be able to:

• Create a Watson Visual Recognition service and obtain the API key value.
• Use Visual Recognition API methods to:
▪ Classify images.
▪ Detect faces in an image.
▪ Recognize text in an image.
• Create and train a custom model.

© Copyright IBM Corp. 2018, 2019 14-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Unit 15. Designing and building an

intelligent solution
Estimated time
00:45

Overview
This unit explains the benefits of integrating multiple Watson services to build a comprehensive
intelligent solution. This unit presents two intelligent solutions use cases: A cognitive banking FAQ
chatbot and an intelligent procurement system.

© Copyright IBM Corp. 2018, 2019 15-1

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Unit objectives
• Explain the need to integrate multiple IBM Watson services to build an
intelligent solution.
• Describe the general outline for the integration of IBM Watson Assistant
with other services and applications.
• Explain the key concepts that enable Watson Assistant integration.
• Describe the integration flow between IBM Watson Assistant, IBM
Watson Discovery, IBM Watson Natural Language Understanding, and
IBM Watson Tone Analyzer to build the cognitive banking chatbot.
• Describe the integration flow between IBM Watson Knowledge Studio
and Watson Discovery.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-1. Unit objectives

© Copyright IBM Corp. 2018, 2019 15-2

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
15.1. Integrating IBM Watson services to build a
solution

© Copyright IBM Corp. 2018, 2019 15-3

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Integrating IBM Watson

services to build a solution

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-2. Integrating IBM Watson services to build a solution

This section describes the benefits of integrating multiple AI services and introduces typical
applications that you can create by combining multiple Watson services.

© Copyright IBM Corp. 2018, 2019 15-4

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Topics
• Integrating IBM Watson services to build a solution
• Watson Assistant integration with other services
• Watson Assistant, Discovery, Natural Language Understanding, and
Tone Analyzer integration flow
• Knowledge Studio and Watson Discovery integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-3. Topics

© Copyright IBM Corp. 2018, 2019 15-5

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Benefits
• A single Watson service adds artificial intelligence (AI) capabilities to
the application in one specific area.

• Integrating multiple Watson services adds more than one AI capability

to the application, which enhances the application with richer cognitive
capabilities.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-4. Benefits

Using one Watson service adds artificial intelligence (AI) capabilities to the application in one
specific area.
Integrating multiple Watson services adds more than one AI capability to the application, which
enhances the application with richer cognitive capabilities.

© Copyright IBM Corp. 2018, 2019 15-6

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Building solutions with Watson services

Watson services on IBM Cloud are a set of REST APIs:
• Easy to integrate as solution components.
• Must be integrated with other parts of a solution, for example, back-end
systems, social media channels, and more.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-5. Building solutions with Watson services

Watson services on IBM Cloud are a set of REST APIs. They are easy to use as a component of a
solution within an application. They must be integrated with various other parts of the solution so
that your users can interact with your instance of the Watson service.
The figure shows examples of applications that can be built by integrating multiple Watson
services:
• Sentiment, personality, and tone analysis: This application integrates three Watson services to
process tweets from users and analyze sentiment (Natural Language Understanding), tone
(Tone Analyzer), and the personality of the user (Personality Insights).
• Real-time transcription: This Android application performs real-time transcription and translation
by integrating IBM Watson Speech to Text, IBM Watson Text to Speech, and IBM Watson
Language Translator services.
An application orchestrates the services integration and provides the logic of the solution.

© Copyright IBM Corp. 2018, 2019 15-7

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Resources for the integration of Watson services

Assets that are available to assist with the integration:
• Watson SDKs
• API Reference and documentation
• Watson Starter Kits

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-6. Resources for the integration of Watson services

Although IBM provides several assets to help the integration effort, such as Watson SDKs, API
references, and sample applications, other users have contributed GitHub repositories too. There
are endless possibilities for the integration of Watson services with other channels or specific
external systems.
It is not possible to cover the broad range of options and possibilities for integrating Watson
services. This presentation provides an introduction to Watson services integration and an example
that is implemented in the exercise that follows the presentation.
References:
Watson SDKs: https://console.bluemix.net/docs/services/watson/getting-started-sdks.html#sdks
API reference and documentation: https://console.bluemix.net/developer/watson/documentation
Watson Starter Kits: https://console.bluemix.net/developer/watson/starter-kits

© Copyright IBM Corp. 2018, 2019 15-8

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
15.2. Watson Assistant integration with other
services

© Copyright IBM Corp. 2018, 2019 15-9

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Watson Assistant integration

with other services

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-7. Watson Assistant integration with other services

This section introduces the integration of Watson Assistant with other Watson services and
channels.

© Copyright IBM Corp. 2018, 2019 15-10

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Topics
• Integrating IBM Watson services to build a solution
• Watson Assistant integration with other services
• Watson Assistant, Discovery, Natural Language Understanding, and
Tone Analyzer integration flow
• Knowledge Studio and Watson Discovery integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-8. Topics

© Copyright IBM Corp. 2018, 2019 15-11

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Watson Assistant integration: General outline

Application

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-9. Watson Assistant integration: General outline

Although it is impossible to describe how to integrate with every possible integration point, there is
a general outline that most integrations follow. The following major components are parts of a
solution that integrates chatbots with other services and applications:
1. Front end or channel: This component can be a web page or an application window where the
users type their questions, the responses are shown, images are displayed, and so on. It might
be a messaging channel, an embedded chat widget, a mobile app, or even SMS messaging.
2. Watson Assistant: The “intelligence” behind the interaction is the Watson Assistant service.
Watson Assistant takes the inputs, understands them, and drives what takes place next. Some
examples of the output are displaying a response, detecting the intent of what is being asked,
using a multi-modal interaction like showing a map, playing a video, or something more
complex, such as reading from and writing to a database or even calling an enterprise service.
Watson Assistant can be trained on your content, but the interaction follows some structure.
Depending upon the content source or type, you might have to use some data transformation or
connectivity patterns.
3. Application layer: This is the middle layer, which varies the most across different solutions.  
There is one job that this layer must accomplish: Passing information from the front end to the
chatbot (Watson Assistant), including system context, and passing it back to carry the
conversation. It is a translation layer that moves data from one side to the other and back.

© Copyright IBM Corp. 2018, 2019 15-12

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
4. Pre-processing: The flow gets more complex if you have additional interactions that you want
to integrate. For example, suppose that you want to add Tone Analyzer to build an empathetic
chatbot. This action is typically called pre-processing because it happens before calling Watson
Assistant. The application layer takes the user input, runs it through this pre-processor layer, in
this case to get the tone of the user statement, attaches the response, in this case tone analysis
results as context for Watson Assistant, and then pass it on to Watson Assistant.
5. Post-processing: This is the step where the logic that is necessary to respond to the user
query is. It happens after calling Watson Assistant but before returning a response to the
front-end layer. The Watson Discovery service is an example of a post-processing service.
Another use case for the post-processing layer is writing information to a database. For
example, a user orders a large pepperoni pizza. Your application might have to make two
callouts. The first call places the order in your point of sale (POS) system to order the pizza, and
the second call might write the order to a database. This way, the next time the user logs in,
they can say “order my usual” or something similar. Watson Assistant typically returns some
action for your application to perform and it also returns some text. Your application can do the
activities that are defined, and then show a message such as “I’ll remember that it is your
favorite, and it’s on the way. Thank you for your order.” Another approach is to directly call
external services from the Watson Assistant dialog to enrich your conversation or allow users to
complete activities by using post-processing.
Reference: Integrate Watson Assistant With Just About Anything, found at:
https://medium.com/ibm-watson/integrate-watson-assistant-with-just-about-anything-695bc1d2987
5

© Copyright IBM Corp. 2018, 2019 15-13

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Key concepts to enable Watson Assistant integration

Communicating with the Watson services:
ƒ Create a wrapper for the Watson service.
ƒ Specify the service credentials.
ƒ Specify the service version.
ƒ Watson SDKs provide mechanisms for instantiating a service wrapper for
several programming languages.
ƒ Example for Watson Assistant in Node.js:

// Sets up Assistant service wrapper

var AssistantV2 = require('watson-developer-cloud/assistant/v2');

// Set up Assistant service wrapper.

var service = new AssistantV2({
iam_apikey: '{apikey}', // replace with API key
version: '2018-09-20'
});

var assistantId = '{assistant_id}'; // replace with assistant ID

var sessionId;

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-10. Key concepts to enable Watson Assistant integration

The first step is to create a wrapper for the Watson Assistant service.
The wrapper is an object to which you send input and receive output from the service. When you
create the service wrapper, specify the authentication credentials from the service key and the
version of the Watson Assistant API (and the other services) that you use.
In this Node.js example, the wrapper is an instance of AssistantV2, which is stored in the
variable service.
The Watson SDKs for other languages provide equivalent mechanisms for instantiating a service
wrapper.

© Copyright IBM Corp. 2018, 2019 15-14

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Key concepts to enable Watson Assistant integration (cont.)

Context:
ƒ It maintains state information.
ƒ It is an object that is passed back and forth between your application and the
Watson Assistant service.
ƒ Your application must maintain the context from one turn of the conversation
to the next.
ƒ Also used to store other data that you want to pass between your application
and the Watson Assistant service. Examples:
• Persistent data that you want to maintain throughout the conversation, such
as a customer's name or account number.
• Any data that you want to track, such as the status of the option settings.
ƒ In each round of the conversation, send back the response.context
object that was received in the previous round.

service.message({
input: { text: newMessageFromUser },
context : response.context,
}, processResponse)

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-11. Key concepts to enable Watson Assistant integration (cont.)

State information for your conversation is maintained by using the context. The context is an object
that is passed between your application and the Watson Assistant service. It is the responsibility of
your application to maintain the context from one turn of the conversation to the next. The context
includes a unique identifier for each conversation with a user, and a counter that is incremented
with each turn of the conversation.
In addition to maintaining your place in the conversation, the context can also be used to store any
other data that you want to pass between your application and the Watson Assistant service. This
information can include persisting the data that you want to maintain throughout the conversation
(such as a customer's name or account number), or any other data that you want to track (such as
the status of option settings).
The context contains variables that are meant to be persistent. To pass information from one call to
the next, the application developer must pass the previous API call's response context with each
subsequent API call. For example, the dialog can collect the user's name and then refer to the user
by name in subsequent nodes.

© Copyright IBM Corp. 2018, 2019 15-15

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Key concepts to enable Watson Assistant integration (cont.)

Context variable:
ƒ A context variable is a variable that you define in a dialog node or from an
application.
ƒ Optionally, you can specify a default value for a context variable.
ƒ Nodes and application logic can change its value.
ƒ Example: Your application sets a $time_of_day context variable, and
passes it to the dialog node, which can use the information to tailor the
greeting it displays to the user.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-12. Key concepts to enable Watson Assistant integration (cont.)

A context variable is a variable that you define in a node or in the application, and optionally specify
a default value for it.
You can pass information from the application to the dialog by setting a context variable and
passing the context variable to the dialog.
For example, your application can set a $time_of_day context variable, and pass it to the dialog,
which can use the information to tailor the greeting it shows to the user.
In this example, the dialog knows that the application sets the variable to one of these
values: morning, afternoon, or evening. It can check for each value, and depending on which value
is present, return the appropriate greeting. If the variable is not passed or has a value that does not
match one of the expected values, then a more generic greeting is displayed to the user.
The dialog can also add context variables to pass information from one node to another or to
update the values of context variables. As the dialog asks for and gets information from the user, it
can track the information and reference it later in the conversation. For example, in one node you
might ask users for their name, and in a later node address them by name.

© Copyright IBM Corp. 2018, 2019 15-16

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
References:
https://www.ibm.com/cloud/garage/architectures/cognitiveConversationDomain
https://console.bluemix.net/docs/services/conversation/dialog-actions.html#dialog-actions
https://www.ibm.com/blogs/bluemix/2017/11/enhance-chatbot-conversation-context-variables-syst
em-entities/

© Copyright IBM Corp. 2018, 2019 15-17

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Key concepts to enable Watson Assistant integration (cont.)

Using intents, entities, and context for application and Watson Assistant
integration:
ƒ Watson Assistant identifies intents and entities in the user’s input.
ƒ The Watson Assistant dialog passes intent, entities, and context to the
application.
ƒ The application performs specific tasks that are based on intent, entity,
and context values.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-13. Key concepts to enable Watson Assistant integration (cont.)

In general, any integration between the application and Watson Assistant is done by using intents,
entities, and context objects:
• Watson Assistant dialog detects the intents and entities in the user’s response.
• Watson Assistant dialog passes the intents, entities, and context objects to the application in
JSON format.
• The application performs specific tasks according to the intents, entities, and context values
that are sent to the application.

© Copyright IBM Corp. 2018, 2019 15-18

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Key concepts to enable Watson Assistant integration (cont.)

ƒ Callback function:
í A function that is passed into another function as an argument.
í A callback function is called at the completion of a task.
ƒ Using the callback function for application and Watson Assistant
integration:
í Application calls the assistant.message API by passing the payload
object and callback function in its arguments.
í Watson Assistant processes the task, sets the output, intents, entities, and
context in the response, and then returns to the callback function.
í The response is processed by the application in the callback function.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-14. Key concepts to enable Watson Assistant integration (cont.)

Callback is an asynchronous equivalent for a function. A callback function is called at the

completion of a task.
The callback function is used in the application and Watson Assistant integration:
1. The application calls the assistant.message API by passing the payload object and the
callback function in its arguments.
2. Watson Assistant processes the task and sets the output, which is the chatbot response,
intents, entities, and context in the response to the API, and then returns back to the callback
function.
3. In the callback function, the response containing the output, intents, entities, and context is
processed.

© Copyright IBM Corp. 2018, 2019 15-19

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Making programmatic calls from a dialog node

ƒ Calling external applications or services. Use cases:
í Include the weather forecast in the chatbot.
í Validate information that was collected from the user.
í Perform calculations.
í Check a flight status that is provided by an air traffic service.
í Interact with an external application, for example, restaurant reservations.
ƒ Approaches for integration:
í Create an orchestration application that acts as the middle layer between Watson
Assistant and the external service.
í Call the external service directly from Watson Assistant dialog node.
ƒ IBM Cloud Functions:
í A Function-as-a-Service (FaaS) platform based on Apache OpenWhisk that runs
functions in response to incoming events or direct invocations.
í Provide a set of small, distinct, and independent actions.
í Developers focus on the application logic and creating actions that are run on demand.
í Cloud Functions actions contain your function code and are started by events or REST
API calls.
í Cloud Functions actions can be called from a dialog node.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-15. Making programmatic calls from a dialog node

There are many reasons to call external applications or services to have richer interactions in the
chatbot’s dialogs. The typical way of achieving such integration is to create an orchestration
application. This orchestration application is the glue logic between Watson Assistant and an
external service. This approach is described in this presentation and the exercise that follows.
However, another approach is for a Watson Assistant dialog node to call the external service
directly. This approach enables your client application to call the external service or use IBM Cloud
Functions.
IBM Cloud Functions is based on Apache OpenWhisk. It is a Function-as-a-Service (FaaS) platform
that runs functions in response to incoming events or direct invocations.

© Copyright IBM Corp. 2018, 2019 15-20

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Watson Assistant integration architecture with Cloud Functions

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-16. Watson Assistant integration architecture with Cloud Functions

The figure show the general outline for integration introduced earlier in this presentation but in this
case, the architecture includes IBM Cloud Functions as the orchestration component. In this case,
Watson Assistant calls the external service directly by using Cloud Functions.

© Copyright IBM Corp. 2018, 2019 15-21

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Making programmatic calls from a dialog node (cont.)

Defining a programmatic call in a dialog node
ƒ Add an actions array to the node by using the JSON editor.
ƒ The actions array specifies the programmatic calls to make from the dialog.
ƒ Store the response that is received from the service in a context variable and use
it to condition the node’s response.
{
"context": {
"variable_name" : "variable_value"
},
"actions": [
{
"name":"<actionName>",
"type":"client | cloud_function | server | web_action",
"parameters": {
"<parameter_name>":"<parameter_value>",
"<parameter_name>":"<parameter_value>"
},
"result_variable": "<result_variable_name>",
"credentials": "<reference_to_credentials>"
}
],
"output": {
"text": "response text"
}

}
Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-17. Making programmatic calls from a dialog node (cont.)

To make programmatic calls directly from a dialog node, add an actions array to the node by using
the JSON editor.
The actions array specifies the programmatic calls to make from the dialog. It can define up to five
separate programmatic calls. The actions array includes action name, parameters list, and the
response from the external function or service.
The figure shows the syntax to define the programmatic call:
• <actionName>: The name of the action or service to call.
• <type>: Indicates the type of call to make. Choose from the following types:
▪ client: Sends a message response with programmatic call information in a standardized
format that your external client application can use to perform the call or function, and get a
result on behalf of the dialog. The JSON object in the response body specifies the service or
function to call, any associated parameters to pass with the call, and how the result should
be sent back.
▪ cloud_function: Calls an IBM Cloud Functions action (one or more) directly. You must
define the action itself separately by using IBM Cloud Functions.
▪ web_action: Calls an IBM Cloud Functions web action (one or more) directly. You must
define the web action itself separately by using IBM Cloud Functions.

© Copyright IBM Corp. 2018, 2019 15-22

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
• <action_parameters>: Any parameters that are expected by the external program, which is
specified as a JSON object.
• <result_variable_name>: The name to use to reference the JSON object that is returned by
the external service or program. The result is stored as a context variable so it can be displayed
in the node response or accessed by dialog nodes that are triggered later.
Reference:
https://console.bluemix.net/docs/services/conversation/dialog-actions.html#dialog-actions

© Copyright IBM Corp. 2018, 2019 15-23

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
15.3. Watson Assistant, Discovery, Natural
Language Understanding, and Tone
Analyzer integration flow

© Copyright IBM Corp. 2018, 2019 15-24

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Watson Assistant, Discovery,

Natural Language
Understanding, and Tone
Analyzer integration flow

Cognitive banking chatbot application

example

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-18. Watson Assistant, Discovery, Natural Language Understanding, and Tone Analyzer integration flow

This section describes the integration flow that is implemented by the cognitive banking chatbot
application. This flow is a practical example of integrating multiple Watson services, an application
that orchestrates the services integration, and back-end banking systems.

© Copyright IBM Corp. 2018, 2019 15-25

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Topics
• Integrating IBM Watson services to build a solution
• Watson Assistant integration with other services
• Watson Assistant, Discovery, Natural Language Understanding, and
Tone Analyzer integration flow
• Knowledge Studio and Watson Discovery integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-19. Topics

© Copyright IBM Corp. 2018, 2019 15-26

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Integration example: Cognitive banking chatbot

• The cognitive banking chatbot demonstrates how the Watson Assistant
dialog is enhanced by integrating with the following items:

ƒ Natural Language Understanding to identify entities.

ƒ Tone Analyzer to detect the user’s emotions.
ƒ Discovery to retrieve answers from a collection of FAQ documents.

• This unit explains the integration flow of the solution.

ƒ Exercise 11 describes the step-by-step implementation.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-20. Integration example: Cognitive banking chatbot

The cognitive banking chatbot provides an example of integration of multiple Watson services. The
Watson Assistant dialog is enhanced by adding capabilities that are provided by other Watson
APIs:
• Natural Language Understanding to identify entities
• Tone Analyzer to detect the user’s emotions
• Discovery to retrieve answers from a collection of FAQ documents
Exercise 11 shows the full implementation steps for the “Cognitive banking chatbot” solution.

© Copyright IBM Corp. 2018, 2019 15-27

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Cognitive banking chatbot integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-21. Cognitive banking chatbot integration flow

Cognitive banking chatbot integration flow:

1. The FAQ documents are added to the Discovery collection.
2. The user interacts with a chatbot through the application UI.
3. The user input is processed with Tone Analyzer to detect anger. An anger score is added to the
context.
4. The user input is processed with Natural Language Understanding. The context is enriched with
Natural Language Understanding-detected entities and keywords, for example, a location.
5. The input and enriched context is sent to Assistant. Assistant recognizes intent, entities, and
dialog paths. It responds with a reply or action.
6. Optionally, a requested action is performed by the application, which might include one of the
following items:
a. Look up additional information from bank services to append to the reply.
b. Use Discovery to reply with an answer from the FAQ documents.

© Copyright IBM Corp. 2018, 2019 15-28

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Building the cognitive banking chatbot application

1. Create the Watson services on IBM Cloud:
ƒ Watson Assistant
ƒ Natural Language Understanding
ƒ Tone Analyzer
ƒ Discovery

2. Import the skill (formerly workspace) to Watson Assistant.

3. Load the Discovery documents.
4. Associate the application with each Watson service instance:
ƒ Get the services credentials from IBM Cloud.
ƒ Set the service credentials in the .env file of the Node.js
application.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-22. Building the cognitive banking chatbot application

This section describes, at a high level, how the cognitive banking chatbot solution is built by using a
Node.js application as the orchestration application:
1. Create the Watson services (Watson Assistant, Natural Language Understanding, Tone
Analyzer, and Discovery) on IBM Cloud.
2. Import the pre-developed workspace (skill in Watson Assistant V2) to the Watson Assistant
service.
3. Load the FAQ documents in to the Discovery service.
4. Get the service credentials from the services on IBM Cloud, then set them in the .env file of the
Node.js application.

© Copyright IBM Corp. 2018, 2019 15-29

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Building the cognitive banking chatbot application (cont.)

5. Set up the communication with Watson services from the
Node.js app:
ƒ Import each Watson service SDK.
ƒ Initialize each service with the service credentials and version.
6. Send input from the application to the Watson Assistant
service:
ƒ Use the service’s message API.
ƒ Set the workspace ID (Skill ID) in the payload.
ƒ Set the user’s input in the payload.
ƒ Set the context object in the payload to maintain the state of
the conversation.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-23. Building the cognitive banking chatbot application (cont.)

5. To set up the communication with the Watson services from Node.js application, complete the
following steps:
▪ Import the Watson services SDKs to the Node.js application.
▪ Initialize each service with the credentials and the required version of the API.
6. Send the user’s input to the Watson Assistant service:
▪ Use the message API of the Watson Assistant service.
▪ Set the Workspace ID (Skill ID) in the payload of the API.
▪ Set the user’s input in the payload of the API.
▪ Set the context in the payload of the API to maintain the state of the conversation.
▪ Set the callback function in the API arguments to process the response that is returned from
the API.

© Copyright IBM Corp. 2018, 2019 15-30

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Building the cognitive banking chatbot application (cont.)

7. Receive and process the response from Watson Assistant:
ƒ After the message API finishes, it returns the response to the
callback function.
ƒ The response data that is returned contains:
• Intents
• Entities
• Output
• Context
ƒ Intents, entities, output, and context are set from the Watson
Assistant dialog nodes.
ƒ The output contains the Watson Assistant dialog response to
the user.
ƒ The context checks whether it contains an action object:
ƒ If there is an action object: Process the action to either get the response
from the back-end service or from a Discovery query to the FAQ
documents collection.
ƒ If there is no action object: The output is returned to the user “as is”.
Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-24. Building the cognitive banking chatbot application (cont.)

7. To receive and process the response from the Watson Assistant service:
▪ After the message API finishes, it returns the response to the callback function to be
processed.
▪ The response that is returned contains the intents, entities, output, and the context that
were set from the Watson Assistant dialog nodes.
▪ The output contains the response of the Watson Assistant dialog.
▪ Context is checked from the Node.js application to see whether it contains the “action”
object:
- If there is an action object: Process the action to either get the response from the
back-end service or from a Discovery query to the FAQ documents collection.
- If no action is found: The output of Watson Assistant dialog is returned to the user as is.

© Copyright IBM Corp. 2018, 2019 15-31

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Build cognitive banking chatbot application (cont.)

8. Check whether the user is angry by using Tone Analyzer:
ƒ Use the service’s tone API.
ƒ Set the user’s input in the payload body.
ƒ The response data that is returned contains the score of the
user’s tone. If an angry tone is detected, the angry score is
added to the Watson Assistant context.
9. Detect location in the user’s questions by using Natural
Language Understanding:
ƒ Use the service’s analyze API.
ƒ Set the user’s input in the payload body.
ƒ Select the entities and keywords as the features in the
payload body.
ƒ The response data that is returned contains the entity type
Location if location is present in the user’s input. If the
Location entity is detected, the Location is added to the
Watson Assistant context.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-25. Build cognitive banking chatbot application (cont.)

8. The Node.js application checks for the user’s tone by using the Tone Analyzer service as
follows:
▪ It uses the tone API of the service.
▪ The user’s input is set in the payload of the API, and the callback function is passed in its
arguments.
▪ The API returns the response data in the callback function, which contains the user’s tone
scores. If the user is angry, the API returns an angry tone type and score. The application
sets the angry score in the context to be sent to the Watson Assistant service afterward.

© Copyright IBM Corp. 2018, 2019 15-32

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
9. The Node.js application detects the location in the user’s question by using the Natural
Language Understanding service as follows:
▪ It uses the analyze API of the service.
▪ The user’s input is set in the payload of the API.
▪ The features object, which contains the entities and keywords, is set in the payload.
▪ The callback function is also passed in its arguments to process the response of the API.
▪ The API returns the response data in the callback function, which contains the entities and
keywords that were detected. If a location is detected in the user’s input, the application sets
the Location in the context to be sent to the Watson Assistant service afterward.

© Copyright IBM Corp. 2018, 2019 15-33

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Building the cognitive banking chatbot application (Cont.)

10. Generate the chatbot response by using Discovery:
ƒ If the Watson Assistant context contains action to get a
response from Discovery:
ƒ Use the service’s query API.

ƒ Set the user’s input in the payload.

ƒ The response data that is returned contains the response to be returned
to the user.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-26. Building the cognitive banking chatbot application (Cont.)

10. The Node.js application sends a response to the user from the Discovery service FAQ
documents as follows:
▪ If the Watson Assistant dialog sets an “action” context with the value that indicates that the
application must generate the response from Discovery:
- The application uses the query API of the Discovery service.
- The user’s input is set in the payload of the API, and the callback function is passed in
its arguments to process the returned response.
- The response data that is returned contains the response that must be returned to the
user.

© Copyright IBM Corp. 2018, 2019 15-34

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty
15.4. Knowledge Studio and Watson Discovery
integration flow

© Copyright IBM Corp. 2018, 2019 15-35

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Knowledge Studio and

Watson Discovery integration
flow

Intelligent procurement system example

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-27. Knowledge Studio and Watson Discovery integration flow

© Copyright IBM Corp. 2018, 2019 15-36

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Topics
• Integrating IBM Watson services to build a solution
• Watson Assistant integration with other services
• Watson Assistant, Discovery, Natural Language Understanding, and
Tone Analyzer integration flow
• Knowledge Studio and Watson Discovery integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-28. Topics

© Copyright IBM Corp. 2018, 2019 15-37

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Intelligent procurement system

• The intelligent procurement system demonstrates how to use Watson
Knowledge Studio and Watson Discovery to enhance the analysis of
shipping and procurement information.

• Instead of hiring experts to analyze the reports that are captured from
data sources, this solution provides expert analysis that is based on
Watson Knowledge Studio and Discovery.

• This unit describes the integration flow of the solution.

ƒ Exercise 12 shows the step-by-step implementation.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-29. Intelligent procurement system

Currently, customers perform analyses of various market reports on their own or hire experts to
make procurement decisions. These experts analyze reports that are captured from data sources, a
process that can be time-consuming and prone to human error, which potentially might cause a
chain effect of issues that can impact production. This code pattern explains how to create a
complete end-to-end solution for a procurement use case. With this intelligent procurement system,
which is based on Watson Knowledge Studio (WKS) and Watson Discovery, a customer can
receive expert analysis more quickly and accurately.
Exercise 12 shows the full implementation steps for the “Intelligent procurement system” solution.

© Copyright IBM Corp. 2018, 2019 15-38

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Intelligent procurement system integration flow

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-30. Intelligent procurement system integration flow

Intelligent procurement system integration flow:

1. Load the type system and corpus files into Watson Knowledge Studio.
2. A user generates a model by training and evaluating data.
3. The Knowledge Studio model is deployed to Watson Discovery.
4. An application queries Watson Discovery for procurement data.
5. A user uses the app to select a query to perform, which retrieves the data from Watson
Discovery.

© Copyright IBM Corp. 2018, 2019 15-39

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Unit summary
• Explain the need to integrate multiple IBM Watson services to build an
intelligent solution.
• Describe the general outline for the integration of IBM Watson Assistant
with other services and applications.
• Explain the key concepts that enable Watson Assistant integration.
• Describe the integration flow between IBM Watson Assistant, IBM
Watson Discovery, IBM Watson Natural Language Understanding, and
IBM Watson Tone Analyzer to build the cognitive banking chatbot.
• Describe the integration flow between IBM Watson Knowledge Studio
and Watson Discovery.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-31. Unit summary

© Copyright IBM Corp. 2018, 2019 15-40

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Review questions
1. True or False:
It is better to integrate just one Watson service to add
cognition to the application.

2. Which service can be integrated with the Watson Assistant

to detect the user’s anger?
A. Natural Language Classifier
B. Tone Analyzer
C. Watson Discovery
D. Anger Detection

3. True or False:
Integrating a custom model created for a particular domain
by using Knowledge Studio with Discovery service enables
organizations to get expert analysis of their document
collections.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-32. Review questions

© Copyright IBM Corp. 2018, 2019 15-41

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Review questions (cont.)

4. Which Watson service is used to analyze and search data in
human-readable documents?
A. Watson Knowledge Studio
B. Natural Language Understanding
C. Watson Discovery
D. Language Translator

5. Which item maintains the conversation state information?

A. Callback function
B. Entity
C. Context
D. REST API

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-33. Review questions (cont.)

© Copyright IBM Corp. 2018, 2019 15-42

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Review answers
1. True or False: It is better to integrate just one Watson service to
add cognition to the application.

2. Which service can be integrated with the Watson Assistant to

detect the user’s anger?
A. Natural Language Classifier
B. Tone Analyzer
C. Watson Discovery
D. Anger Detection

3. True or False: Integrating a custom model created for a

particular domain by using Knowledge Studio with
Discovery service enables organizations to get
expert analysis of their document collections.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-34. Review answers

© Copyright IBM Corp. 2018, 2019 15-43

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Review answers (cont.)

4. Which Watson service is used to analyze and search data
inside human-readable documents?
A. Watson Knowledge Studio
B. Natural Language Understanding
C. Watson Discovery
D. Language Translator
The answer is C.

5. Which item maintains the conversation state information?

A. Callback function
B. Entity
C. Context
D. REST API

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-35. Review answers (cont.)

© Copyright IBM Corp. 2018, 2019 15-44

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Exercise: Creating a cognitive

banking FAQ chatbot

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-36. Exercise: Creating a cognitive banking FAQ chatbot

© Copyright IBM Corp. 2018, 2019 15-45

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Exercise objectives
• This exercise introduces you to the cognitive banking FAQ
chatbot application.
• In this application the Watson Assistant flow is enhanced by
adding capabilities provided by other Watson APIs such as
Watson Natural Language Understanding, Tone Analyzer, and
Discovery.
• The objective is to design and implement a solution that
integrates several Watson services by using the IBM Watson
Node.js SDK.
• After completing this exercise, you should be able to:
ƒ Create a chatbot by using Watson Assistant and Node.js.
ƒ Use Watson Discovery with passage retrieval to find answers in
FAQ documents.
ƒ Use Watson Tone Analyzer to detect emotion in a conversation.
ƒ Identify entities by using Watson Natural Language
Understanding.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-37. Exercise objectives

After completing this exercise, you should be able to:

• Create a chatbot by using Watson Assistant and Node.js.
• Use Watson Discovery with passage retrieval to find answers in FAQ documents.
• Use Watson Tone Analyzer to detect emotion in a conversation.
• Identify entities by using Watson Natural Language Understanding.

© Copyright IBM Corp. 2018, 2019 15-46

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Exercise: Integrating Watson

Knowledge Studio with
Discovery for the procurement
domain

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-38. Exercise: Integrating Watson Knowledge Studio with Discovery for the procurement domain

© Copyright IBM Corp. 2018, 2019 15-47

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.2
Unit 15. Designing and building an intelligent solution

Uempty

Exercise objectives
• This exercise shows you how to integrate a machine learning
model from IBM Watson Knowledge Studio with the Discovery
service to provide custom entity and relations enrichments for
the procurement domain.
• After completing this exercise, you should be able to:
ƒ Create a machine learning model in Watson Knowledge Studio
and deploy it to Watson Discovery.
ƒ Create a Watson Discovery custom configuration and leverage a
Watson Knowledge Studio model to enrich entities and relations.
ƒ Integrate a custom model from Watson Knowledge Studio with the
Discovery service to provide custom entity and relations
enrichments customized for a specific procurement domain.

Designing and building an intelligent solution © Copyright IBM Corporation 2019

Figure 15-39. Exercise objectives

After completing this exercise, you should be able to:

• Create a machine learning model in Watson Knowledge Studio and deploy it to Watson
Discovery.
• Create a Watson Discovery custom configuration and leverage a Watson Knowledge Studio
model to enrich entities and relations.
• Integrate a custom model from Watson Knowledge Studio with the Discovery service to provide
custom entity and relations enrichments customized for a specific procurement domain.

© Copyright IBM Corp. 2018, 2019 15-48

Course materials may not be reproduced in whole or in part without the prior written permission of IBM.
V11.3

backpg

© Copyright International Business Machines Corporation 2018, 2019.