Academia.eduAcademia.edu

Figure 1 – uploaded by IJIRCST I

See full PDFdownloadDownload figure
would be solved. But a sentence can have several possible interpretations; therefore the AI based system adopted a strategy for combining syntactic and semantic constraint. In 1960’s and 70’s, majority of the systems were based on AI methodology. These systems tried to produce semantics for the whole sentence to determine its meaning and from this semantic representation, word ambiguity problem

Table 1 would be solved. But a sentence can have several possible interpretations; therefore the AI based system adopted a strategy for combining syntactic and semantic constraint. In 1960’s and 70’s, majority of the systems were based on AI methodology. These systems tried to produce semantics for the whole sentence to determine its meaning and from this semantic representation, word ambiguity problem

Related Figures (3)

Word sense disambiguation is the task of automatically determining the correct sense of a word within a text. A word may be used in a variety of contexts with a variety of meanings. Each of these meanings is called a word sense. Now-a-days, determining the correct sense of a word has been the subject of research. In figure 1, NLP trinity has been shown. NLP trinity includes Language, Problem and algorithm. There are different natural languages such as Hindi, French, English, Gujarati, etc. And every language has problems or challenges such as Part-of-speech tagging, morph analysis, parsing, etc. Each problem can be solved with algorithms such as HMM, CRF, MEMM.
Word sense disambiguation is the task of automatically determining the correct sense of a word within a text. A word may be used in a variety of contexts with a variety of meanings. Each of these meanings is called a word sense. Now-a-days, determining the correct sense of a word has been the subject of research. In figure 1, NLP trinity has been shown. NLP trinity includes Language, Problem and algorithm. There are different natural languages such as Hindi, French, English, Gujarati, etc. And every language has problems or challenges such as Part-of-speech tagging, morph analysis, parsing, etc. Each problem can be solved with algorithms such as HMM, CRF, MEMM.
In figure 2, it gives the pictorial description of the basic idea of the strategy. The idea behind using the intersection similarity measure is to capture the belief that there will be high overlap between the words in the context and the related words found from the wordnet lexical and semantic relations and glosses. ‘C9 ILL”. But here it is used in the context of first meaning.
In figure 2, it gives the pictorial description of the basic idea of the strategy. The idea behind using the intersection similarity measure is to capture the belief that there will be high overlap between the words in the context and the related words found from the wordnet lexical and semantic relations and glosses. ‘C9 ILL”. But here it is used in the context of first meaning.
senses. The most common lexicon used in this method are: machine readable dictionaries, thesauri and computational It depends on lexical resources to disambiguate word
senses. The most common lexicon used in this method are: machine readable dictionaries, thesauri and computational It depends on lexical resources to disambiguate word
Related topics:
Computational Linguistics
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved