该文提出了一种基于卷积树核函数的中文实体语义关系抽取方法,该方法通过在关系实例的结构化信息中加入实体语义信息,如实体类型、引用类型和GPE角色等,从而构造能有效捕获结构化信息和实体语义信息的合一句法和实体语义关系树,以提高中文语义关系抽取的性能。在ACE RDC 2005中文基准语料上进行的关系探测和关系抽取的实验表明,该方法能显著提高中文语义关系抽取性能,大类抽取的最佳F值达到67.0,这说明结构化句法信息和实体语义信息在中文语义关系抽取中具有互补性。
Abstract
This paper proposes a convolution tree kernel-based approach to Chinese semantic relation extraction. It constructs a unified syntactic and entity semantic tree by incorporating entity semantic information, such as entity type, entity subtype and mention type etc., into the structural information of a relation instance. The motivation behind this approach is to effectively capture both the structural and entity semantic information in a unified way in order to boost the predictive performance of relation extraction. Evaluation on the ACE RDC 2005 Chinese benchmark corpus shows that our method significantly improves the performance of Chinese semantic relation extraction, specifically achieving the highest F-measure of 67.0 on the top-level relation extraction, and exhibits the complementation of the structure of syntactic information and semantic information in Chinese Semantic Relation Extraction.
Key wordsChinese semantic relation extraction; convolution tree kernel; entity semantic information
关键词
中文语义关系抽取 /
卷积树核函数 /
实体语义信息
{{custom_keyword}} /
Key words
Chinese semantic relation extraction /
convolution tree kernel /
entity semantic information
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Nanda Kambhatla. Combining lexical, syntactic and semantic features with Maximum Entropy models for extracting relations[C]//ACL. Morristown,NJ,USA, 2004: 178-181.
[2] Zhou GuoDong, Su Jian, Zhang Jie, et al. Exploring various knowledge in relation extraction[C]//ACL, 2005: 427-434.
[3] Zhao S. B. and Grishman R. Extracting relations with integrated information using kernel methods [C]// ACL. Ann Arbor, USA, 2005: 419-426.
[4] Wang Ting, Li Yaoyong, Kalina Bontcheva, et al. Automatic Extraction of Hierarchical Relations from Text[C]// Proceedings of the Third European Semantic Web Conference (ESWC 2006), 2006: 401-416.
[5] 车万翔, 刘挺, 李生. 实体关系自动抽取[J]. 中文信息学报, 2005, 19(2): 1-6.
[6] 董静, 孙乐, 冯元勇, 黄瑞红. 中文实体关系抽取中的特征选择研究[J]. 中文信息学报, 2007: 21(4): 80-85, 91.
[7] Li W. J., Zhang P., Wei F. R., Hou Y. X., and Lu Q. A Novel Feature-based Approach to Chinese Entity Relation Extraction[C]//ACL.Columbus,Ohio,USA, 2008: 89-92.
[8] Zelenko D, Aone C, Richardella A. Kernel methods for relation extraction [J]. Journal of Machine Learning Research, 2003,3(2003): 1083-1106.
[9] Culotta A, Sorensen J. Dependency tree kernels for relation extraction [C]//ACL.Barcelona, Spain,2004:423-429.
[10] Bunescu R. C, Raymond J. M. A Shortest Path Dependency Kernel for Relation Extraction [C]// EMNLP. Vancover, B.C,2005:724-731..
[11] Zhang M., Zhang J., Su J., and Zhou G. D. A Composite Kernel to Extract Relations between Entities with both Flat and Structured Features [C]// COLING-ACL. Sydney, Australia,2006:825-832.
[12] Zhou G. D., Zhang M., Ji D. H., and Zhu Q. M. Tree Kernel-based Relation Extraction with Context-Sensitive Structured Parse Tree Information [C]//EMNLP/CoNLL’2007.Prague Czech,2007:728-736.
[13] Qian L. H., Zhou G. D., Zhu Q. M., et al. Exploiting constituent dependencies for tree kernel-based semantic relation extraction[C]//COLING’2008. Manchester,UK,2008:697-704.
[14] Che W. X., Jiang, J. M. Su Z., Pan Y., and Liu T. Improved-Edit-Distance Kernel for Chinese Relation Extraction [C]//Proceedings of the 2nd international Joint Conference on Natural Language Processing (IJCNLP’05).Jeju Island, Korea,2005:134-139.
[15] 刘克彬, 李芳, 刘磊, 韩颖. 基于核函数中文关系自动抽取系统的实现[J].计算机研究与发展, 2007, 44(8): 1406-1411.
[16] Huang R. H., Sun L., and Feng Y. Y. Study of Kernel-Based Methods for Chinese Relation Extraction [C]//LNCS (Lecture Notes in Computer Science). Springer Berlin/Heidelberg, 2008: 598-604.
[17] Collins M. and Duffy N. Covolution kernels for natural language [C]//NIPS’2001:Cambridge, MA,2001:625-632.
[18] 庄成龙,钱龙华,周国栋. 基于树核函数的实体语义关系抽取方法研究[J]. 中文信息学报,2009,23(1):1-8.
[19] 黄瑞红,孙乐,冯元勇,黄云平. 基于核方法的中文实体关系抽取研究[J].中文信息学报,2008,22(5): 102-108.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家863计划资助项目(2006AA01Z147);国家自然科学基金资助项目(60673041, 60873150);国家教育部博士点基金资助项目(200802850006); 江苏省自然科学基金资助项目(BK2008160);江苏省高校自然科学重大基础研究项目(08KJA520002)
{{custom_fund}}
PDF(704 KB)
