Approach Toward Word Sense Disambiguation for the English-To-Sanskrit Language Using Naive Bayesian Classification

Natural language processing (NLP) refers to the ability of a computer program capacity to understand both spoken and written human languages. Word Sense Disambiguation (WSD) is a method for separating words with similar meanings and determining the words with the precise significance of meaning. It is an essential and critical application for all NLP tasks. Several methodological approaches come up in the context of WSD. There are supervised and unsupervised WSD approaches that are widely used in the disambiguation process. Supervised WSD approaches have shown better results than unsupervised approaches. The Naive Bayesian (NB) classifiers approach is known as one of the best methods among all the supervised approaches for WSD. NB is a classification algorithm that is based on the Bayes theorem and it simplifies learning by accepting that features are independent of a given class. In this paper, we use an NB classifier to disambiguate ambiguous English words by predicting part-of-speech inclusive of "noun,""verb,""adverb," and "adjective." This disambiguation module is an enhancement in machine translation. The system reported the performance measure of eighty-five percent of the scale of F1-measure.