Archives

A Novel approach to Word Sense Disambiguation for Marathi Sentence Using Supervised Methodology


Swati.G.Kale,ShitalTelrandhe,U.H.Gawande,
Abstract

Word sense disambiguation (WSD) is one of the attention gaining research problem in area of natural language processing. This may called as conjunctional problem in which depending upon the context of the sentence the meaning of the disambiguate word is assigned computationally. Automatic selection of the sense has key importance in many applications of NLP, such as Information Retrieval (IR), Information Extraction (IE),Machine Translation (MT), Question Answering (QT), Content Analysis, Word Processing, Lexicography and Semantic Web etc. WSD is considered as AI-complete problem and Machine Learning approach will be effective to solve this problem. Sizeable work has been done for WSD for foreign languages but for Indian languages this issue is still open challenge. Marathi, a morphologically rich language spoken by domestic people of Maharashtra State in India. Now a days many official ,ecommerce work has been done in Marathi, which may face the problem of identifying the correct sense of word. In this paper the exploration of main methods to solve WSD problem has been done and proposes the machine learning algorithm to solve WSD for Marathi . We have evaluated its performance on 220 Marathi sentences.

Volume 11 | 08-Special Issue

Pages: 3082-3087