Anaphora Resolution in Hindi

Abstract

Natural language processing (NLP) is way of understanding the human languages by machine which involves the field of computer science and artificial intelligence. The basic aim of NLP is to develop such software that will analyze, understand and generate human languages. It has many challenges like word sense disambiguation, sentiment analysis, summarize from paragraph to sentences, correct the search query, language detection, missing apostrophes, etc, anaphora is one of them. Anaphora is considered as the problem of referring pronoun phrase to noun phrase with n the sentence or between the sentences. Anaphora resolution is required in various NLP applications like auto summarization system, machine translation system, question answering system etc. Lot of work has been done in English but less work has been done in Hindi. Anaphora Resolution in Hindi is a complex task because Hindi is free word order language. It is based on the verb so pronouns in Hindi show a great deal of dubiety. This thesis presents the various approaches like Ruble based, Machine based, Learning based etc to resolve various issues of anaphora resolution in Hindi. Firstly, the thesis proposes an algorithm by using rule based approach to resolve pronouns based on gender and number agreement which gave 79% of accuracy in terms of F-Score.