Leveraging Chinese Encyclopedia for Weakly Supervised Relation Extraction

详细信息    查看全文

• 关键词：Relation extraction ; Weakly supervised ; SVM ; Baidu Encyclopedia
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9544
• 期：1
• 页码：127-140
• 全文大小：1,683 KB
• 参考文献：1.Zelenko, D., Aone, C., et al.: Kernel methods for relation extraction. J. Mach. Learn. Res. 3, 1083–1106 (2003)MathSciNet MATH
  2.Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the AC, pp. 1003–1011 (2009)
  3.Fader, A., Soderland, S., Etzioni, O.: Identifying relations for open information extraction. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pp. 1535–1545 (2011)
  4.Thomas, P., Neves, M., et al.: Relation extraction for drug-drug interactions using ensemble learning. In: Drug-Drug Interaction Extraction, Huelva, Spain, pp. 11–18 (2011)
  5.Surdeanu, M., Tibshirani, J., et al.: Multi-instance multi-label learning for relation extraction. In: Conference on Empirical Methods in Natural Language Processing and Natural Language Learning, Jeju Island, Korea, pp. 455–465 (2012)
  6.Li, H., Wu, X., et al.: A relation extraction method of Chinese named entities based on location and semantic features. Appl. Intell. 38(1), 1–15 (2013)CrossRef
  7.He, T., Xu, C., et al.: Named-entity relation extraction method based on seed self-expansion. Comput. Eng. 32(21), 183–184, 193 (2006)
  8.Xu, F., Wang, T., Chen, H., et al.: SVM-based Chinese entity relation extraction. In: 9th Chinese National Conference on Computational Linguistics, Dalian, China, pp. 497–502 (2007)
  9.Chen, P., Guo, J., et al.: Chinese field entity relation extraction based on convex combination kernel function. J. Chin. Inf. Process. 27(5), 144–148 (2013)
  10.Zeng, D., Zhao, J., et al.: Open entity attribute-value extraction from unstructured text. J. Jiangxi Norm. Univ. (Nat. Sci. Ed.) 37(3), 279–283 (2013)
  11.Guo, X., He, T., et al.: Chinese named-entity relation extraction based on the syntactic and semantic features. J. Chin. Inf. Process. 28(6), 183–189 (2014)
  12.Zhang, H., Huang, M., Zhu, X.: A unified active learning framework for biomedical relation extraction. J. Comput. Sci. Technol. 27(6), 1302–1313 (2012)CrossRef
  13.Platt, J.C.: Fast training of support vector machines using sequential minimal optimization. In: Advances in Kernel Methods. MIT Press, pp. 185–208 (1999)
  14.Xianyi, C., Qian, Z.: A study of relation extraction of undefined relation type based on semi-supervised learning framework. J. Nanjing Univ. Nat. Sci. 48(4), 466–474 (2012)
  15.Wang, H., Qi, Z., Hao, H., Xu, B.: A hybrid method for chinese entity relation extraction. In: Zong, C., Nie, J.-Y., Zhao, D., Feng, Y. (eds.) NLPCC 2014. CCIS, vol. 496, pp. 357–367. Springer, Heidelberg (2014)
  16.Zhen, J., Dake, H.E., et al.: Relation extraction from Chinese online encyclopedia based on weakly supervised learning. CAAI Trans. Intell. Syst. 10(1), 113–119 (2015)
  
• 作者单位：Xiyue Guo (17) (19)
  Tingting He (18)
  
  17. National Engineering Research Center for E-learning, Central China Normal University, Wuhan, 430079, China
  19. School of Information Technology, Xingyi Normal University for Nationalities, Xingyi, 562400, China
  18. School of Computer, Central China Normal University, Wuhan, 430079, China
  
• 丛书名：Semantic Technology
• ISBN：978-3-319-31676-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

In the research of named-entity relation extraction based on supervision, selecting relation features for traditional methods are usually finished by people, and it’s hard to implement these methods for large-scale corpus. On the other hand, fixing relation types is the premise, so the practicabilities of these methods are not so ideal. This paper presents a weakly supervised method for Chinese named-entity relation extraction without man-made annotations, and the relation types in this method are not chosen artificially. The method collects entity relation types from the structured knowledge in encyclopedia pages, and then automatically annotates the relation instances existing in the texts based on these relation types. Simultaneously, the syntactic and semantic features of entity relations will be considered in this method, then the machine learning data will be completed, finally we use Support Vector Machine (SVM) model to train relation classifiers from training data, and these classifiers could try to extract entity relations from testing data. We carry out the experiment with the data from Chinese Baidu Encyclopedia pages, and the results show the effectiveness of this method, the overall F1 value reaches to 83.12 %. In order to probe the universality of this method, we also use the acquired relation classifiers to extract entity relations from news texts, and the results manifest that this method owns certain universality.