Probabilistic neural network approach to the classification of demonstrative pronouns for indirect anaphora in Hindi

In this paper, we propose the application of probabilistic neural networks (PNNs) to the classification scheme of demonstrative pronouns for indirect anaphora in Hindi corpus. The Demonstrative Pronouns in Hindi, ''yeh''(this/it), ''veh''(that/those), ''iss''(this/it), and ''uss''(that/those) can be personal or demonstrative. The differentiation can be ascertained from only the situation or the context. The case marking of pronouns further add the constraints on linguistic patterns. We propose to cast such an anaphora as a semantic inference process, which encompasses several salient linguistic characteristic features such as grammatical role, proximity, syntactic category and semantic cues. Our focus of study is demonstrative pronouns without noun phrase antecedent in Hindi written corpus. We analyzed 313 news items having 3890 sentences, 3101 pronouns, of which 608 instances covered those demonstrative pronouns, which had 183 instances with non-NP-antecedents. The effectiveness of the approach is demonstrated through set of simulations and evaluations.

[1]  Donna K. Byron,et al.  Resolving Pronominal Reference to Abstract Entities , 2002, ACL.

[2]  Whitney Gegg-Harrison,et al.  Identifying Non-Referential it: A Machine Learning Approach Incorporating Linguistically Motivated Patterns , 2005, ACL 2005.

[3]  Chris Brew,et al.  Lexical Clustering and Definite Description Interpretation , 1998 .

[4]  Richard Evans,et al.  Enhancing Preference-Based Anaphora Resolution with Genetic Algorithms , 2000, Natural Language Processing.

[5]  Grigori Sidorov,et al.  WORD CHOICE PROBLEM AND ANAPHORA RESOLUTION , 2006 .

[6]  M. Tanenhaus,et al.  Beyond salience: Interpretation of personal and demonstrative pronouns , 2005 .

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  J. Srinivas,et al.  Neural Networks: Algorithms and Applications , 2002 .

[9]  Kalina Bontcheva,et al.  Corpus Linguistics and South Asian Languages: Corpus Creation and Tool Development , 2004, Lit. Linguistic Comput..

[10]  Michael Hegarty,et al.  Cognitive Status, Information Structure, and Pronominal Reference to Clausally Introduced Entities , 2003, J. Log. Lang. Inf..

[11]  Alice Davison.  Lexical anaphors and pronouns in Hindi/Urdu , 2000 .

[12]  D. F. Specht,et al.  Probabilistic neural networks for classification, mapping, or associative memory , 1988, IEEE 1988 International Conference on Neural Networks.

[13]  Ron Zacharski,et al.  Directly and Indirectly Anaphoric Demonstrative and Personal Pronouns in Newspaper Articles , .

[14]  Bonnie L. Webber,et al.  Structure and Ostension in the Interpretation of Discourse Deixis , 1991, ArXiv.

[15]  Shalom Lappin,et al.  An Algorithm for Pronominal Anaphora Resolution , 1994, CL.

[16]  Richard Evans,et al.  Applying Machine Learning Toward an Automatic Classification of It , 2001, Lit. Linguistic Comput..

[17]  Ron Zacharski,et al.  Pronouns without NP antecedents: how do we know when a pronoun is referential? , 2005 .

[18]  Michel J. Denber,et al.  A utomatic Resolution of Anaphora in English , 1998 .

[19]  C. D. Paice,et al.  Towards the automatic recognition of anaphoric features in English text: the impersonal pronoun “it” , 1987 .

[20]  Michael Strube,et al.  Dialogue Acts, Synchronizing Units, and Anaphora Resolution , 2000, J. Semant..

[21]  Ken Barker,et al.  Indirect anaphora resolution as semantic path search , 2005, K-CAP '05.

[22]  Tony McEnery,et al.  Demonstratives in English , 2001 .

[23]  António Branco,et al.  Anaphora processing : linguistic, cognitive and computational modelling , 2005 .

[24]  Branimir Boguraev,et al.  Anaphora for Everyone: Pronominal Anaphora Resolution without a Parser , 1996, COLING.

[25]  Yamuna Kachru,et al.  Relational grammar, ergativity, and Hindi-Urdu , 1977 .