Scribd
Upload
4 views

NLP Syllabus

The document outlines the course DS6222 Natural Language Processing offered by Emerald International College, detailing its objectives, prerequisites, and teaching methods. It covers foundational and advanced topics in NLP, including text processing, sentiment analysis, machine translation, and ethical considerations. The course requires a minimum attendance of 80% and includes a structured outline of weekly topics and recommended textbooks.

Uploaded by

Abinet Sf
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
4 views

NLP Syllabus

The document outlines the course DS6222 Natural Language Processing offered by Emerald International College, detailing its objectives, prerequisites, and teaching methods. It covers foundational and advanced topics in NLP, including text processing, sentiment analysis, machine translation, and ethical considerations. The course requires a minimum attendance of 80% and includes a structured outline of weekly topics and recommended textbooks.

Uploaded by

Abinet Sf
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Emerald International College: School of Computing and Analytics

Course Number DS6222


Course Title Natural Language Processing
Credit hour 3 (5 ECTS)
Degree program MSc in Data Science
Course Description This course provides an overview of natural language processing, exploring
techniques for analyzing and generating human language. Students will learn
foundational concepts, algorithms, and applications in NLP, including text
processing, sentiment analysis, and machine translation, along with advanced
topics like transfer learning, unsupervised learning, and ethical considerations.

Course Objectives and At the end of the course, the students will be expected to:
outcomes  To acquire a basic understanding of linguistic concepts and
natural language complexity, and variability;
 To acquire a basic understanding of machine learning
techniques as applied to language;
 To implement N-grams Models.
Prerequisites  Basic knowledge of Python programming
 Familiarity with linear algebra and probability

Teaching and Lecture, Paper Review, Assignments and Demonstrations, Project


Learning work,
Attendance Requirements’ Class attendance is mandatory for all lectures with minimum
requirement of 80% attendance.

Course Outline
Week 1: Introduction to NLP
 Overview of NLP
 Applications of NLP
 Challenges in NLP
 Linguistic concepts: syntax, semantics, and pragmatics
 Parts of speech tagging
 Morphology and word formation
 Text normalization: tokenization, stemming, lemmatization
 Stop words and n-grams
 Text representation: Bag of Words, TF-IDF
Week 2:
Word Embeddings
 Introduction to word embeddings
 Word2Vec and GloVe
 Contextual embeddings: ELMo, BERT
Language Models
 Introduction to language modeling
 N-gram models
 Neural language models
Week 3:
Sentiment Analysis
 Sentiment classification techniques
 Feature extraction for sentiment analysis
 Case studies and applications
Sequence Modeling
 Introduction to RNNs and LSTMs
 GRUs and their applications
 Sequence-to-sequence models
Week 4:
Machine Translation
 Overview of machine translation techniques
 Statistical vs. neural machine translation
 Evaluation metrics for translation
Named Entity Recognition (NER)
 Techniques for NER
 Rule-based vs. machine learning approaches
 Applications of NER
Week 5:
Advanced Topics in NLP
 Transfer Learning in NLP: Fine-tuning pre-trained models
 Few-shot and Zero-shot Learning: Techniques and applications
Text Generation
 Introduction to text generation
 Generative models: GPT, Transformer
 Applications in creative writing and chatbots
Dialogue Systems
 Types of dialogue systems: task-oriented vs. open-domain
 Dialogue management and response generation
 Case studies of successful dialogue systems
Week 6:
Current Trends and Future Directions
 Recent advancements in NLP (e.g., large language models, multimodal models)
 Future challenges in NLP research
 Discussion of ongoing research topics
Ethics in NLP
 Bias in NLP models
 Privacy and data usage
 Responsible AI practices

Recommended Textbooks
1) Jurafsky, D., and Martin, J.H., Speech and Language Processing, 2nd Edn, Prentice
Hall, 2008
2) Bird, S., Klein, E., Loper, E. (2009). Natural Language Processing with Python,
O'Reilly, 2009
3) Manning, Christopher D., and Hinrich Schütze. Foundations of Statistical
Natural Language Processing. Cambridge, MA: MIT Press, 1999
4) Allen J, Natural language understanding (2nd ed).
Benjamin/Cummings, 1995
5) Jurafsky, David, and James H. Martin. Speech and Language Processing: An
Introduction to Natural Language Processing, Computational Linguistics and Speech
Recognition. Upper Saddle River, NJ: Prentice-Hall, 2000

You might also like