Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
In this paper we propose a competition learning approach to coreference resolution. Traditionally, supervised machine learning approaches adopt the singlecandidate model. Nevertheless the preference relationship between the antecedent candidates cannot be determined accurately in this model. By contrast, our approach adopts a twin-candidate learning model. Such a model can present the competition criterion for antecedent candidates reliably, and ensure that the most preferred candidate is selected. Furthermore, our approach applies a candidate filter to reduce the computational cost and data noises during training and resolution. . | Coreference Resolution Using Competition Learning Approach Xiaofeng Yang Guodong Zh ou Institute for Infocomm Research 21 Heng Mui Keng Terrace Singapore 119613 xiaofengy zhougd sujian @ i2r.a-star.edu.sg Abstract In this paper we propose a competition learning approach to coreference resolution. Traditionally supervised machine learning approaches adopt the singlecandidate model. Nevertheless the preference relationship between the antecedent candidates cannot be determined accurately in this model. By contrast our approach adopts a twin-candidate learning model. Such a model can present the competition criterion for antecedent candidates reliably and ensure that the most preferred candidate is selected. Furthermore our approach applies a candidate filter to reduce the computational cost and data noises during training and resolution. The experimental results on MUC-6 and MUC-7 data set show that our approach can outperform those based on the singlecandidate model. 1 Introduction Coreference resolution is the process of linking together multiple expressions of a given entity. The key to solve this problem is to determine the antecedent for each referring expression in a document. In coreference resolution it is common that two or more candidates compete to be the antecedent of an anaphor Mitkov 1999 . Whether a candidate is coreferential to an anaphor is often determined by the competition among all the candidates. So far various algorithms have been proposed to determine the preference relationship between two candidates. Mitkov s knowledge-poor pronoun resolution method Mitkov 1998 for example uses the scores from a set of antecedent indicators Jian Su Chew Lim Tan Department of Computer Science National University of Singapore Singapore 117543 yangxiao tancl @comp.nus.edu.sg to rank the candidates. And centering algorithms Brennan et al. 1987 Strube 1998 Tetreault 2001 sort the antecedent candidates based on the ranking of the forward-looking or backwardlooking