Exploiting Zero Pronouns to Improve Chinese Coreference Resolution

Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 278–288, Seattle, Washington, USA, 18-21 October 2013. c⃝2013 Association for Computational Linguistics Exploiting Zero Pronouns to Improve Chinese Coreference Resolution Fang Kong Department of Computer Science National University of Singapore 13 Computing Drive Singapore 117417 dcskf@nus.edu.sg Hwee Tou Ng Department of Computer Science National University of Singapore 13 Computing Drive Singapore 117417 nght@comp.nus.edu.sg Abstract Coreference resolution plays a critical role in discourse analysis. This paper focuses on exploiting zero pronouns to improve Chi- nese coreference resolution. In particular, a simplified semantic role labeling framework is proposed to identify clauses and to detect zero pronouns effectively, and two effective methods (refining syntactic parser and refining learning example generation) are employed to exploit zero pronouns for Chinese coreference resolution. Evaluation on the CoNLL-2012 shared task data set shows that zero pronouns can significantly improve Chinese coreference resolution. 1 Introduction As one of the most important tasks in discourse analysis, coreference resolution aims to link a given mention (i.e., entity or event) to its co-referring ex- pression in a text and has been a focus of research in natural language processing (NLP) for decades. Over the last decade, various machine learning techniques have been applied to coreference reso- lution and have performed reasonably well (Soon et al., 2001; Ng and Cardie, 2002; Fernandes et al., 2012). Current techniques rely primarily on surface level features such as string match, syntactic features such as apposition, and shallow semantic features such as number, gender, semantic class, etc. Despite similarities between Chinese and English, there are differences that have a significant impact on coreference resolution. In this paper, we focus on exploiting one of the key characteristics of Chi- nese text, zero pronouns (ZPs), to improve Chinese coreference resolution. In particular, a simplified se- mantic role labeling (SRL) framework is proposed to identify Chinese clauses and to detect zero pro- nouns effectively, and two effective methods are em- ployed to exploit zero pronouns for Chinese corefer- ence resolution. Experimental results show the ef- fectiveness of our approach in improving the perfor- mance of Chinese coreference resolution. Our work is novel in that it is the first work that incorporates the use of zero pronouns to significantly improve Chinese coreference resolution The rest of this paper is organized as follows. Section 2 describes our baseline Chinese corefer- ence resolution system. Section 3 motivates how the detection of zero pronouns can improve Chinese coreference resolution, using an illustrating exam- ple. Section 4 presents our approach to detect zero pronouns. Section 5 proposes two methods to ex- ploit zero pronouns to improve Chinese coreference resolution, based on a corpus study and preliminary experiments. Section 6 briefly outlines the related work. Finally, we conclude our work in Section 7. 2 Chinese Coreference Resolution According to Webber (1978), coreference resolu- tion can be decomposed into two complementary subtasks: (1) anaphoricity determination: decid- ing whether a given noun phrase (NP) is anaphoric or not; and (2) anaphora resolution: linking to- …

Content truncated to 500 words