tailieunhanh - Báo cáo khoa học: "Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates"

such as the existence and properties of its antecedents. In fact, such information has been used for pronoun resolution in many heuristicbased systems. The S-List model (Strube, 1998), for example, assumes that a co-referring candidate is a hearer-old discourse entity and is preferred to other hearer-new candidates. In the algorithms based on the centering theory (Brennan et al., 1987; Grosz et al., 1995), if a candidate and its antecedent are the backwardlooking centers of two subsequent utterances respectively, the candidate would be the most preferred since the CONTINUE transition is always ranked higher than SHIFT or RETAIN. . | Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates Xiaofeng Yangff Jian Su Guodong Zhou Chew Lim Tam Institute for Infocomm Research 21 Heng Mui Keng Terrace Singapore 119613 xiaofengy sujian zhougd @ Abstract Coreferential information of a candidate such as the properties of its antecedents is important for pronoun resolution because it reflects the salience of the candidate in the local discourse. Such information however is usually ignored in previous learning-based systems. In this paper we present a trainable model which incorporates coreferential information of candidates into pronoun resolution. Preliminary experiments show that our model will boost the resolution performance given the right antecedents of the candidates. We further discuss how to apply our model in real resolution where the antecedents of the candidate are found by a separate noun phrase resolution module. The experimental results show that our model still achieves better performance than the baseline. 1 Introduction In recent years supervised machine learning approaches have been widely explored in reference resolution and achieved considerable success Ge et al. 1998 Soon et al. 2001 Ng and Cardie 2002 Strube and Muller 2003 Yang et al. 2003 . Most learning-based pronoun resolution systems determine the reference relationship between an anaphor and its antecedent candidate only from the properties of the pair. The knowledge about the context of anaphor and antecedent is nevertheless ignored. However research in centering theory Sidner 1981 Grosz et al. 1983 Grosz et al. 1995 Tetreault 2001 has revealed that the local focusing or centering also has a great effect on the processing of pronominal expressions. The choices of the antecedents of pronouns usually depend on the center of attention throughout the local discourse segment Mitkov 1999 . To determine the salience of a candidate in the local context we may need to check the .