In this paper we present our report on anaphora resolution for Hindi language. Anaphora resolution is a key problem in natural language processing, and has correspondingly received a significant amount of attention in the literature. The primary focus of this work is the resolution of pronominal anaphora means binding of pronoun with their intended noun phrase in the discourse. Though the significant amount of work has been done in English and other European languages, the efficient work, in Hindi language, is lagging far behind. The complete paper is divided into four sections. First section of the paper presents a review of work done in the field of anaphora resolution in Hindi language. In the next section we cover issues related to syntactic and semantic structure of Hindi and influence of cases on pronouns. Further we define constraint sources which will form the base of anaphora resolution task. Finally we perform manual experiment on different kinds of data sets and corresponding results are obtained which shows final accuracy of approx 71%.
[1]
Rashmi Prasad,et al.
Constraints on the generation of referring expressions, with special reference to hindi
,
2003
.
[2]
Saroj Kaushik,et al.
Application of Pronominal Divergence and Anaphora Resolution in English-Hindi Machine Translation
,
2009,
Polytech. Open Libr. Int. Bull. Inf. Technol. Sci..
[3]
Michael Strube,et al.
Discourse Salience and Pronoun Resolution in Hindi
,
2000
.
[4]
Saroj Kaushik,et al.
Probabilistic neural network approach to the classification of demonstrative pronouns for indirect anaphora in Hindi
,
2010,
Expert Syst. Appl..
[5]
Saroj Kaushik,et al.
Machine Learning Approach for the Classification of Demonstrative Pronouns for Indirect Anaphora in Hindi News Items
,
2011,
Prague Bull. Math. Linguistics.
[6]
Akshar Bharati,et al.
Reference and Ellipsis in an Indian Languages Interface to Databases
,
2009
.