Scribd
Upload
10 views

Brainware University: Name:Srinjoy Sarkar Student CODE:BWU/BTA/21/099 Semester:6 Section:B Program Name:B-Tech C Se (Aiml)

Uploaded by

Sohini Ghosh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
10 views

Brainware University: Name:Srinjoy Sarkar Student CODE:BWU/BTA/21/099 Semester:6 Section:B Program Name:B-Tech C Se (Aiml)

Uploaded by

Sohini Ghosh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

N A M E : S R I N J OY

SARKAR

STUDENT
C O D E : BW U / B TA / 2 1 / 0 9 9
SEMESTER:6

BRAINWARE SECTION:B

UNIVERSITY P R O G R A M N A M E : B -T E C H
CSE(AIML)
COURSE CODE:PEC-
CSM602C

COURSE NAME:SPEECH AND


N AT U R A L L A N G UA G E P R O C E SS I N G
TOPIC:DISCOURSE AMBIGUITY
CONTENTS

INTRODUCTION OF DISCOURSE REAL WORLD


REFERENCES
AMBIGUITY AMBIGUITY IMPLICATIONS

TECHNIQUES TO
TYPES OF ANAPHORIC
SOLVE DISCOURSE
AMBIGUITY AMBIGUITY
AMBIGUITY
AMBIGUITY
INTRODUCTION

• An expression having more than one


meaning.

• Uncertainty in choosing the right


meaning of a sentence.

EXAMPLE:
1. The chicken is ready to eat.

2. I can play cricket.


3. Give me the can.

4. Bank –Finance bank


5. Bank-River Bank
TYPES OF AMBIGUITY

AMBIGUITY

LEXICAL SEMANTIC DISCOURSE


SYNTACTIC AMBIGUITY PRAGMATIC AMBIGUITY
AMBIGUITY AMBIGUITY AMBIGUITY
DISCOURSE
AMBIGUITY
INTRODUCTION
• Occurs when meaning of a word or
sentence is unclear due to its context .

• Meaning depends on surrounding


conversation.

• A sentence can have many interpretations.


EXAMPLE
1. John told Bob that he failed. 3. Mary said she loves Peter. He
Ans-Here ‘he’- can be john or was delighted.
Bob Ans-Here ‘He’ can have two
meaning

2. He said he would come ,but I


don’t think he meant it.
Ans-Here ‘he’ – does specify
anyone
ANAPHORIC
AMBIGUITY
EXAMPLE:
INTRODUCTION
1. The horse ran up the hill. It was
very steep. It soon got tired.
• when a word's meaning depends on
previous word.
Ans: Here ‘it’- is pronoun and
• It has two parts Anaphor and antecedent.
‘horse’ and ‘hill’ are
• Noun replaced by Pronoun noun
EXAMPLE:
John called Tom, and he said he would come.
Ans- he-anaphor
John and Tom-antecedent
REAL LIFE
IMPLICATIONS
• Search Engines

• Virtual assistances

• Machine Translation

• Sentiment Analysis
VARIOUS
TECHNIQUES
• Coreference Resolution
Identify which referring expressions(e.g.-pronouns ,
nouns)refer to the same entity.

• Anaphora Resolution
Finding the antecedent of an anaphor.

• Machine Learning Models


Uses various deep learning models .
REFERENCES
• https://www.tutorialspoint.com/all-types-of-ambiguities-in-nlp

• Ambiguity – Wikipedia

• https://www.exploredatabase.com/2020/03/ambiguity-in-natural-language-processing
.html

• Decipher Ambiguity in NLPs for Sharper AI Intelligence (shelf.io)


THANK YOU!

You might also like