Abstract Aiming at noisy data in training data and the insufficient use of negative instances in traditional distant supervision relation extraction methods, a relation extraction method combining clause level distant supervision and semi-supervised ensemble learning is proposed. Firstly, the relation instance set is generated by distant supervision. Secondly, based on clause identification, a denoising algorithm is used to reduce the wrongly labeled data in the relation instance set. Thirdly, the lexical features are extracted from relation instances and are transformed into distributed vectors to establish feature dataset. Finally, all positive data and part of negative data in feature dataset are chosen to form labeled dataset, and the other part of negative data are chosen to form unlabeled dataset. A relation classifier is trained through improved semi-supervised ensemble learning algorithm. Experiments show that compared with baseline methods the proposed method achieves higher accuracies and recall.
Fund:Supported by National Natural Science Foundation of China(No.61332017,60703040), Major Science and Technology Project of Zhejiang Province(No.2015C33002,2013C01046,2011C13042), Project of China Knowledge Centre for Engineering Sciences and Technology(No.CKCEST-2014-1-5)
About author:: YU Xiaokang, born in 1990, master student. His research interests include text mining. CHEN Ling(Corresponding author), born in 1977, Ph.D., associate professor. His research interests include pervasive computing and database. GUO Jing, born in 1988, Ph.D. candidate. His research interests include text mining. CAI Yaya, born in 1990, master student. Her research interests include pervasive computing. WU Yong, born in 1977, engineer. His research interests include cloud computing. WANG Jingchang, born in 1977, master, senior engineer. His research interests include cloud computing.
[1] 李保利,陈玉忠,俞士汶.信息抽取研究综述.计算机工程与应用, 2003, 39(10): 1-5. (LI B L, CHEN Y Z, YU S W. Research on Information Extraction: A Survey. Computer Engineering and Applications, 2003, 39(10): 1-5.) [2] ETZIONI O, BANKO M, SODERLAND S, et al. Open Information Extraction from the Web. Communications of the ACM, 2008, 51(12): 68-74. [3] ZHOU G D, SU J, ZHANG J, et al. Exploring Various Knowledge in Relation Extraction // Proc of the 43rd Annual Meeting on Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2005: 427-434. [4] ZELENKO D, AONE C, RICHARDELLA A. Kernel Methods for Relation Extraction. Journal of Machine Learning Research, 2003, 3: 1083-1106. [5] WANG R, NEUMANN R. Recognizing Textual Entailment Using a Subsequence Kernel Method // Proc of the 22nd Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2007: 937-945. [6] MINTZ M, BILLS S, SNOW R, et al. Distant Supervision for Relation Extraction without Labeled Data // Proc of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg, USA: Association for Computational Linguistics, 2009, II: 1003-1011. [7] RIEDEL S, YAO L M, MCCALLUM A. Modeling Relations and Their Mentions without Labeled Text // Proc of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2010, III: 148-163. [8] HOFFMANN R, ZHANG C, LING X, et al. Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations // Proc of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: Association for Computational Linguistics, 2011, I: 541-550. [9] SURDEANU M, TIBSHIRANI J, NALLAPATI R, et al. Multi-instance Multi-label Learning for Relation Extraction // Proc of the Joint Conference on Empirical Methods in Natural Language Proce-ssing and Computational Natural Language Learning. Stroudsburg, USA: Association for Computational Linguistics, 2012: 455-465. [10] ALFONSECA E, FILIPPOVA K, DELORT J Y, et al. Pattern Learning for Relation Extraction with a Hierarchical Topic Model // Proc of the 50th Annual Meeting of the Association for Computatio-nal Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2012, II: 54-59. [11] TAKAMATSU S, SATO I, NAKAGAWA H. Reducing Wrong Labels in Distant Supervision for Relation Extraction // Proc of the 50th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2012, I: 721-729. [12] FAN M, ZHAO D L, ZHOU Q, et al. Distant Supervision for Relation Extraction with Matrix Completion[C/OL]. [2016-07-23]. https://arxiv.org/pdf/1411.4455v1.pdf. [13] BING L, CHAUDHARI S A, WANG R C, et al. Improving Distant Supervision for Information Extraction Using Label Propagation through Lists[C/OL]. [2016-07-23]. http://101.96.10.60/www.cs.cmu.edu/~lbing/pub/emnlp2015_bing.pdf. [14] SOCHER R, HUVAL B, MANNING C D, et al. Semantic Compositionality through Recursive Matrix-Vector Spaces // Proc of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Stroudsburg, USA: Association for Computational Linguistics, 2012: 1201-1211. [15] ZENG D J, LIU K, CHEN Y B, et al. Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks // Proc of the Conference on Empirical Methods in Natural Language Processing. 2015. DOI: 10.18653/v1/D15-1203. [16] MOLINA A, PLA F. Clause Detection Using HMM // Proc of the Workshop on Computational Natural Language Learning. Stroudsburg, USA: Association for Computational Linguistics, 2001. DOI: 10.3115/1117822.1455688. [17] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed Representations of Words and Phrases and Their Compositionality[C/OL]. [2016-07-23]. https://arxiv.org/pdf/1310.4546v1.pdf. [18] BLUM A, MITCHELL T. Combining Labeled and Unlabeled Data with Co-training // Proc of the 11th Annual Conference on Computational Learning Theory. New York, USA: ACM, 1998: 92-100. [19] ZHOU Z H, LI M. Tri-training: Exploiting Unlabeled Data Using Three Classifiers. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(11): 1529-1541. [20] ANGLUIN D, LAIRD P. Learning from Noisy Examples. Machine Learning, 1988, 2(4): 343-370.
2017, Vol. 30 
