Graph Connectivity for Unsupervised Word Sense Disambiguation for HINDI Language

Word Sense Disambiguation (WSD) aims to identify the correct sense of a word in a given sentence. WSD is considered to be an open and AI-hard problem in Natural Language Processing (NLP). WSD is most important in many applications like Machine Translation (MT), Information Retrieval (IR), Information Extraction (IE), Text mining, and Lexicography etc. Supervised, Semi-supervised and Unsupervised Approaches to WSD are important and successful learning approaches. In this paper, we proposed the graph-based Unsupervised Word Sense Disambiguation Algorithm to resolve the ambiguity of a word in a given HINDI Language sentence. Finding the proper meaning of a word here implies identification of the most important node from the set of graph nodes which are representing the senses. We make use of HINDI wordnet developed at IIT Bombay as reference library of words to form the sense graph.