Design and Development of a Knowledge-Based Approach for Word Sense Disambiguation by using WordNet for Hindi
Pooja Sharma1, Nisheeth Joshi2

1Pooja Sharma, Department of Computer Science, Banasthali Vidyapith, Jaipur (Rajasthan), India.
2Nisheeth Joshi, Department of Computer Science, Banasthali Vidyapith, Jaipur (Rajasthan), India.
Manuscript received on 05 January 2019 | Revised Manuscript received on 13 January 2019 | Manuscript published on 30 January 2019 | PP: 73-78 | Volume-8 Issue-3, January 2019 | Retrieval Number: C2580018319/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Word Sense Disambiguation (WSD) aims at deciphering word meaning in terms of context with the help of computers. WSD is an accessible and challenging AI-complete problem. WSD analyses word tokens and determine the exact sense of the word being used according to the context. WSD is viewed asafundamental problem in Artificial Intelligence (AI) and Natural Language Processing (NLP). Our problem area involves finding the appropriate sense of a lexeme for available context and relationship between lexicons. This is done using natural language processing techniques which involve queries, NLP specific documents or output texts from Machine Translation (MT). MT automatically translates text from one native language into another. It can be performed on various natural languages like Urdu, Marathi, Punjabi, Bengali, English, and Hindi etc. The different application areas for word sense disambiguation involves SpeechProcessing, Information Retrieval (IR), lexicography, Text Processing and MTetc.With this article, we are exploring the knowledge-based technique for WSD for Hindi. This approach uses explicitly available lexical resources viz. lexicon and thesaurus. It involves incorporating word knowledge from external knowledge resources to removethe equivocalness of words. In this experiment, we tried to develop a WSD tool by considering a knowledge-based approach with WordNet of Hindi. The system uses knowledge-based LESK Algorithm for WSD for Hindi. Our proposed system gives the accuracy of about 71.4%.
Keyword: Word Sense Disambiguation, LESK, WordNet.
Scope of the Article: Design and Diagnosis