A Comprehensive Review of Word Sense Disambiguation Research in few Indian Languages: Implications for Educational Tools

Abstract

Natural Languages are inherently ambiguous. Word Sense Disambiguation is one such problem where one word has multiple meaning depending upon the context in which it appears in the text. It can be considered as an intermediate step for many NLP applications like Machine Translation, Summarization, Query Processing, etc. Developing a Word Sense Disambiguation (WSD) system for the Gujarati language can have significant applications in the education sector. There are different approaches available for WSD which includes Supervised, Unsupervised and knowledge-based approaches. The work done is English language is extensive for
this problem but for other regional languages more research needs to be done. This paper presents various works, mentioning their proposed method, datasets used, limitations and performance for some Indian languages like Hindi, Malayalam, Bengali, etc. The paper also enlists some general observations about existing approaches for word sense disambiguation. In the last section, the paper proposes a method to resolve WSD problem for Gujarati Language using Genetic Algorithm.