Scribd
Upload
60 views9 pages

Unit 2 - Lecture 3

The document discusses Word Sense Disambiguation (WSD) in Natural Language Processing, defining it as the ability to determine the meaning of a word based on context. It highlights the challenges of resolving semantic ambiguity compared to syntactic ambiguity and outlines evaluation methods, approaches, and applications of WSD. Difficulties such as differences in dictionaries and algorithm variance are also noted.

Uploaded by

Niveditha S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
60 views9 pages

Unit 2 - Lecture 3

The document discusses Word Sense Disambiguation (WSD) in Natural Language Processing, defining it as the ability to determine the meaning of a word based on context. It highlights the challenges of resolving semantic ambiguity compared to syntactic ambiguity and outlines evaluation methods, approaches, and applications of WSD. Difficulties such as differences in dictionaries and algorithm variance are also noted.

Uploaded by

Niveditha S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

18CSE359T– Natural Language

Processing

Instructor:
Mrs. S. Niveditha,
Lecture : 12 Assistant Professor(Sr. G)
Unit :2 SRM Institute of Science and Technology,
Session :2 nivedits@[Link]
Topic for Today

 Word Sense disambiguation


Introduction

 Word sense disambiguation, in natural language processing


(NLP), may be defined as the ability to determine which
meaning of word is activated by the use of word in a
particular context.

 Lexical ambiguity, syntactic or semantic, is one of the very


first problem that any NLP system faces.
 Part-of-speech (POS) taggers with high level of accuracy can
solve Word’s syntactic ambiguity.

 On the other hand, the problem of resolving semantic ambiguity


is called WSD (word sense disambiguation).

 Resolving semantic ambiguity is harder than resolving syntactic


ambiguity.

 For example, consider the two examples of the distinct sense that
exist for the word “bass” −

• I can hear bass sound.

• He likes to eat grilled bass.


Evaluation of WSD
 A Dictionary
 The very first input for evaluation of WSD is dictionary, which is
used to specify the senses to be disambiguated.
 Test Corpus
 Another input required by WSD is the high-annotated test
corpus that has the target or correct-senses. The test corpora can
be of two types
 Lexicalsample − This kind of corpora is used in the system,
where it is required to disambiguate a small sample of words.
 All-words − This kind of corpora is used in the system, where it
is expected to disambiguate all the words in a piece of running
text.
Approaches and Methods to Word Sense
Disambiguation (WSD)

 Dictionary-based or Knowledge-based Methods

 Supervised Methods

 Semi-supervised Methods

 Unsupervised Methods
Applications of Word Sense Disambiguation
(WSD)

 Machine Translation

 Information Retrieval (IR)

 Text Mining and Information Extraction (IE)


Difficulties in Word Sense Disambiguation

 Differences between dictionaries

 Different algorithms for different applications

 Inter-judge variance

 Word-sense discreteness
End of session

You might also like