I.J. Intelligent Systems and Applications, 2015, 02, 56-64 Published Online January 2015 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijisa.2015.02.08 Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 02, 56-64 Hybrid Approach to Pronominal Anaphora Resolution in English Newspaper Text Kalyani P. Kamune RKNEC, Department of Computer Science, Nagpur, 440013, India Email: kalyanikamune24@gmail.com Avinash Agrawal RKNEC, Department of Computer Science, Nagpur, 440013, India Email: avinashjagrawal@gmail.com Abstract— One of the challenges in natural language understanding is to determine which entities to be referred in the discourse and how they relate to each other. Anaphora resolution needs to be addressed in almost every application dealing with natural language such as language understanding and processing, dialogue system, system for machine translation, discourse modeling, information extraction. This paper represents a system that uses the combination of constraint- based and preferences-based architectures; each uses a different source of knowledge and proves effective on computational and theoretical basis, instead of using a monolithic architecture for anaphora resolution. This system identifies both inter-sentential and intra-sentential antecedents of “Third person pronoun anaphors” and “Pleonastic it”. This system uses Charniak Parser (parser05Aug16) as an associated tool, and it relays on the output generated by it. Salience measures derived from parse tree are used in order to find out accurate antecedents from the list of all potential antecedents. We have tested the system extensively on 'Reuters Newspaper corpus' and efficiency of the system is found to be 81.9%. Index Terms—Natural Language processing, Anaphora resolution, Discourse, Pronominal Resolution, Co-reference, Discourse Modeling, Artificial Intelligence I. INTRODUCTION Resolution of anaphoric reference is one of the most challenging tasks in the field of natural language processing. It is extremely difficult to give a complete, plausible and computable description of resolution process as we ourselves deal with it only subconsciously and are largely unaware of the particularities. The task of anaphora resolution is even frequently considered to be AI-complete. Anaphora accounts for the cohesion in the text and is active study in formal and computational linguistics alike. Identifying correct anaphora plays a vital role in Natural Language Processing. Automatic resolution of anaphors is crucial task in the understanding of natural language by computers. Understanding of natural language is difficult for computers because natural languages are inherently ambiguous. On the other hand, human beings can easily manage to pick out the intended meaning from the set of possible interpretations unlike computers due to their limited knowledge and inability to get their bearings in complex contextual situations. Ambiguity can be presented at different level. It can be presented at lexical level where one word may have more than one meaning (e.g. bank, chair, files). It can also be presented at syntactical level when more than one structural analysis is possible. Ambiguity can also be presented at semantic level or pragmatic level. The automatic resolution of ambiguity requires a huge amount of linguistic and extra-linguistic knowledge as well as inferring and learning capabilities, and is therefore realistic only in restricted domains. A. Basic Notions and terminologies Cohesion occurs where the interpretation of the some element in the discourse is dependent on that of another and involves the use of abbreviated or alternative linguistics forms which can be recognized and understood by the hearer or the reader .This refers to or replaces previously mentioned items in the spoken or written text. e.g. “Sita is a teacher. Her dream is to visit Paris.” In the above example, it is very normal to observe that second sentence is related to the first sentence and hence we can say that cohesion is present. In the second sentence, ‘her’ refers to ‘Sita’. Now, in the above example, if we replaced ‘her’ by ‘him’, or the whole sentence is replaced by some another isolated sentence, cohesion does not occur any more as the interpretation of second sentence is no longer depends on the first sentence. Discourse features an example of anaphora with the possessive pronoun ’her’ referring to the previously mentioned noun phrase ‘Sita’. [1] Anaphora is described as cohesion which points back to some previous item. The pointing back word or the phrase is called an anaphora and the entity to which it refers or for which it stands is its antecedent. The process of determining antecedent for an anaphora is called anaphora resolution. When the anaphora refers to an antecedent and both have the same referent in the real world, they are termed co-referential. Various terminologies mentioned above like anaphora, antecedent, anaphora resolution and co-referential can be explained well with the help of example as bellow. [3] e.g. “The King is not here yet but he is expected to arrive in the next half an hour.”