Employing the Centering Theory in Pronoun Resolution from the Semantic Perspective

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 987–996, Singapore, 6-7 August 2009. c⃝2009 ACL and AFNLP Employing the Centering Theory in Pronoun Resolution from the Se- mantic Perspective KONG Fang ZHOU GuoDong* ZHU Qiaoming JiangSu Provincial Key Lab for Computer Information Processing Technology School of Computer Science and Technology Soochow University. Suzhou, China 215006 Email: {kongfang, gdzhou, qmzhu}@suda.edu.cn * Corresponding author Abstract In this paper, we employ the centering the- ory in pronoun resolution from the seman- tic perspective. First, diverse semantic role features with regard to different predicates in a sentence are explored. Moreover, given a pronominal anaphor, its relative ranking among all the pronouns in a sentence, ac- cording to relevant semantic role informa- tion and its surface position, is incorporated. In particular, the use of both the semantic role features and the relative pronominal ranking feature in pronoun resolution is guided by extending the centering theory from the grammatical level to the semantic level in tracking the local discourse focus. Finally, detailed pronominal subcategory features are incorporated to enhance the discriminative power of both the semantic role features and the relative pronominal ranking feature. Experimental results on the ACE 2003 corpus show that the centering- motivated features contribute much to pro- noun resolution. 1 Introduction Coreference accounts for cohesion in a text and is, in a sense, the hyperlink for a natural lan- guage. Especially, a coreference instance de- notes an identity of reference and holds between two referring expressions, which can be named entities, definite noun phrases, pronouns and so on. Coreference resolution is the process of link- ing together multiple referring expressions of a given entity in the world. The key in coreference resolution is to determine the antecedent for each referring expression in a text. The ability of linking referring expressions both within a sen- tence and across the sentences in a text is critical to discourse and language understanding in gen- eral. For example, coreference resolution is a key task in information extraction, machine translation, text summarization, and question answering. There is a long tradition of research on coreference resolution within computational lin- guistics. While earlier knowledge-lean ap- proaches heavily depend on domain and linguistic knowledge (Carter 1987; Carbonell and Brown 1988) and have significantly influ- enced the research, the later approaches usually rely on diverse lexical, syntactic and semantic properties of referring expressions (Soon et al., 2001;Ng and Cardie, 2002; Zhou et al., 2004). Current research has been focusing on exploiting semantic information in coreference resolution. For example, Yang et al (2005) proposed a tem- plate-based statistical approach to compute the semantic compatibility between a pronominal anaphor and an antecedent candidate, and Yang and Su (2007) explored semantic relatedness information from automatically discovered pat- terns, while Ng (2007) automatically induced semantic class knowledge from a treebank and explored its application in coreference resolution. Particularly, this paper focuses on the center- ing theory (Sidner,1981;Grosz et al.,1995; Tetreault,2001), which reveals the significant impact of the local focus on …

Content truncated to 500 words