与实体指代不同,事件指代因为其先行词候选是一个事件,与名词性的指代词具有完全不同的语义分类体系,因此适用于实体指代消歧的大多数特征都不能用于事件指代消歧。该文给出了一个基于机器学习方法的事件代词指代消歧平台,详细介绍了平台的实例生成和特征选择过程,并给出了平台在OntoNotes3.0语料上的事件代词指代消歧的结果,对结果进行了分析。从实验结果可以看到,给出的平台获得了较好的系统性能。
Abstract
In event anaphora resolution, the antecedent of the anaphor is an event and the anaphor is a noun phrase. They are parts of different semantic categorization systems, and thus most of features applied in entity anaphora resolution are not appropriate for event anaphora resolution. This paper proposes an event pronoun resolution framework via a machine learning approach. The instances creation and the features selection are presented in detail. This paper also provides the experiment results on OntoNotes 3.0 corpus, confirming pretty good F-measure of the framework.
Key wordsevent pronoun resolution; machine learning approach; instances creation; features selection
关键词
事件代词指代消歧 /
机器学习方法 /
实例生成 /
特征选择
{{custom_keyword}} /
Key words
event pronoun resolution /
machine learning approach /
instances creation /
features selection
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Zheng Chen, Heng Ji. Event Coreference Resolution: Algorithm, Feature Impact and Evaluation[C]//Proceedings of ACL,2009,W09-4303.
[2] Cosmin Adrian Bejan, Sanda Harabagiu. Unsupervised Event Coreference Resolution with Rich Linguistic Features[C]//Proceedings of ACL2010,2010: 1412-1422.
[3] Chen Bin, Su Jian, Tan Chew Lim. A Twin-Candidate Based Approach for Event Pronoun Resolution using Composite Kernel[C]//Proceedings of COLING,2010: 188-196.
[4] Chen Bin, Su Jian, Tan Chew Lim. Resolving Event Noun Phrase to Their Verbal Mentions[C]//Proceedings of EMNLP,2010: 872-881.
[5] Kong Fang, Zhou Guodong. Improving Tree Kernel-based Event Pronoun Resolution with Competitive Information[C]//Proceedings of IJCAI2011.
[6] Soon W.M., Ng H.T., Lim D. A machine learning approach to coreference resolution of noun phrase[C]//Proceedings of Computational Linguistics, 2001, 27(4):521-544.
[7] Kubat M, Matwin S.. Addressing the curse of imbalanced data set: one sided sampling[C]//Proceedings of the 14 International Conference on Machine Learning, 1997:179-186.
[8] Yang X.F., Su J., Tan C.L. Kernel-based pronoun resolution with structured syntactic knowledge[C]//Proceedings of COLING-ACL2006: 41-48.
[9] Zhou G.D., Kong F., Zhu Q.M. Context-sensitive convolution tree kernel for pronoun resolution[C]//Proceedings of IJCNLP2008.
[10] Grosz B.J., Sidner C.L.. Attention, intentions and the structure of discourse[C]//Proceedings of Computational Linguistics. 1986, 12(3): 175- 204.
[11] Ng V, Cardie C. Improving machine learning approaches to Coreference Resolution[C]//Proceedings of ACL, 2002: 104-111.
[12] Collins M., Duffy N.. Covolution kernels for natural language [C]//Proceedings of NIPS2001, 2001: 625-632.
[13] M. Lesk. Automatic sense disambiguation using machine readable dictionaries: How to tell a pine cone from a ice cream cone[C]//Proceedings of SIGDOC ’86, 1986.
[14] Satanjeev Banerjee, Ted Pedersen. An Adapted Lesk Algorithm for Word Sense Disambiguation Using WordNet[C]//Proceedings of CICLing 2002, LNCS 2276, 136-145.
[15] Ted Pedersen ,Siddharth Patwardhan, Jason Michelizzi .WordNet::Similarity - Measuring the Relatedness of Concepts[C]//Proceedings of American Association for Artificial Intelligence (www.aaai.org). 2004.
[16] 王海东,胡乃全,孔芳,等. 指代消解中语义角色特征的研究[J].中文信息学报,2009,(1):23-29.
[17] 陈九昌,孔芳,朱巧明,等.基于树核函数的it待消解项识别研究[J].中文信息学报,2010,(5):24-30.
[18] 王海东,谭魏璇,李艳翠,等.基于树核函数的英文代词消解研究[J].中文信息学报,2009,23(5):33-39.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金资助项目(60873150,90920004,61003153);国家教育部博士点基金资助项目(200802850006,20093201110006)
{{custom_fund}}
PDF(3182 KB)
