An adaptive approach for word sense disambiguation for Hindi language

Abstract

Word sense disambiguation has been a classical problem and it is still considered as a big challenge for NLP researchers. Word vectors have shown remarkable improvements from baseline performances for various NLP challenges. An adaptive approach is developed to resolve the ambiguity at word level using word vectors and presented in this paper. CBOW and Skip-gram models of Word2Vec are used to generate the word embeddings. An input sentence is split into two sets: The first set contains all possible ambiguous words and the second set is constituted from all the unambiguous words. The words from the first set are processed through IndoWordNet to collect all the senses of respective words, and such senses are stored in sensedictionary. An adaptive approach is applied to find out the exact interpretation of the ambiguous word from the sense dictionary for each word from the set of ambiguous words with the context words from the set of unambiguous words. The proposed approach is evaluated on a large scale Hindi corpus and claimed better results than previous attempts.