Gazetteer Method for Resolving Pronominal Anaphora in Hindi Language
Priya Lakhmani, Smita Singh, Pratistha Mathur · 2014
Anaphora processing has been an active topic of research in the field of computational linguistic. At present, resolution of anaphoric reference is one of the most challenging tasks of natural language processing domain. Most of the NLP applications such as machine translation, information extraction, question answering system, automatic summarization etc require successful resolution of anaphora. This paper focuses on pronominal anaphora resolution for Hindi Language using Gazetteer method. We have developed a model that performs pronominal anaphora resolution task for Hindi Language. There are few salient factors among which this model uses Recency factor as the baseline factor. Animistic knowledge is introduced to the model which forms the criteria of classification of different nouns and pronouns. In this paper we demonstrate three experiments conducted on different data sets containing 10 to 30 sentences in Hindi Language along with its summarized result and future directions.