›› 2011, Vol. 26 ›› Issue (1): 45-56.doi: 10.1007/s11390-011-1110-2

• Special Section on Natural Language Processing • Previous Articles     Next Articles

Kernel-Based Semantic Relation Detection and Classification via Enriched Parse Tree Structure

Guo-Dong Zhou (周国栋), Senior Member, CCF, Member, ACM, IEEE and Qiao-Ming Zhu (朱巧明), Senior Member, CCF   

  1. NLP Lab, School of Computer Science and Technology, Soochow University, Suzhou 215006, China
  • Received:2009-12-28 Revised:2010-10-28 Online:2011-01-01 Published:2011-01-01
  • About author:Guo-Dong Zhou received the Ph.D. degree from the National University of Singapore in 1999. He joined the Institute for Infocomm Research, Singapore, in 1999, and had been associate scientist, scientist and associate lead scientist at the institute until August 2006. Currently, he is a professor at the School of Computer Science and Technology, Soochow University, Suzhou, China. His research interests include natural language processing, information extraction and machine learning. He is a senior member of CCF and has been the member of ACM and IEEE since 1999. Currently, he serves as an editorial board member of Computational Linguistics and an associate editor of ACM Transaction on Asian Language Information Processing.
    Qiao-Ming Zhu received his Ph.D. degree from Soochow University, Suzhou, China, in 2008. Currently, he is a professor at the university and acts as the deputy director of Department of Science, Technology and Industry. His research interests include natural language processing, information extraction and embedded systems. He is a senior member of CCF.
  • Supported by:

    Supported by the National Natural Science Foundation of China under Grant Nos. 60873150, 60970056 and 90920004.

PDF

2753

This paper proposes a tree kernel method of semantic relation detection and classification (RDC) between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.

[1] Automatic Content Extraction. http://www.ldc.upenn.edu/rojects/ACE/, 2000-2007.
[2] Haussler D. Convolution kernels on discrete structures. Techical Report UCS-CRL-99-10, University of California, Santa ruzca, USA, 1999.
[3] Vapnik V. Statistical Learning Theory. Chichester: Whiley, K, 1998.
[4] Kambhatla N. Combining lexical, syntactic and semantic feaures with Maximum Entropy models for extracting relaions. In Proc. ACL 2004, Barcelona, Spain, Jul. 21-26, 2004, p.178-181.
[5] Zhao S B, Grishman R. Extracting relations with integrated nformation using kernel methods. In Proc. ACL 2005, Ann rbor, USA, Jun. 25-30, 2005, pp.419-426.
[6] Zhou G D, Su J, Zhang J, Zhang M. Exploring various knowldge in relation extraction. In Proc. ACL 2005, Ann Arbor, SA, Jun. 25-30, 2005, pp.427-434.
[7] Zelenko D, Aone C, Richardella. Kernel methods for relation xtraction. Journal of Machine Learning Research, 2003, 3: 1083-1106.
[8] Culotta A, Sorensen J. Dependency tree kernels for relation xtraction. In Proc. ACL 2004, Barcelona, Spain, Jul. 21-26, 004, pp.423-429.
[9] Bunescu R, Mooney R J. A shortest path dependency kernel or relation extraction. In Proc. HLT/EMNLP2005, Vancouer, Canada, Oct. 6-8, 2005, pp.724-731.
[10] Zhang M, Zhang J, Su J, Zhou G D. A composite kernel to exract relations between entities with both flat and structured eatures. In Proc. COLING-ACL 2006, Sydney, Australia, Jul. 17-21, 2006, pp.825-832.
[11] Collins M, Duffy N. Convolution kernels for natural language. In Proc. NIPS 2001, Vancouver, Canada, Dec. 3-8, 2001, p.625-632.
[12] Zhou G D, Zhang M, Ji D H, Zhu Q M. Tree kernel-based reation extraction with context-sensitive structured parse tree nformation. In Proc. EMNLP-CoNLL 2007, Prague, Czech, Jun. 28-30, 2007, pp.728-736.
[13] Petrov S, Barrett L, Thibaux R, Klein D. Learning accuate, compact and interpretable tree annotation. In Proc. CL 2006, Sydney, Australia, Jul. 17-21, 2006, pp.433-440.
[14] Moschitti A. A study on convolution kernels for shallow parsng. In Proc. ACL 2004, Barcelona, Spain, Jul. 21-26, 2004, p.335-342.
[15] Zhang M, Che W X, Aw A T, Tan C L, Zhou G D, Liu T, Li . A grammar-driven convolution tree kernel for semantic role lassification. In Proc. ACL 2007, Prague, Czech, Jun. 23-30, 2007, pp.200-207.
[16] Moschitti A. Efficient convolution kernels for dependency and onstituent syntactic trees. In Proc. ECML2006, Berlin, ermany, Sept. 18-22, 2006, pp.318-329.
[17] Klein D, Manning C D. Accurate unlexicalized parsing. In Proc. ACL 2003, Sapporo, Japan, Jul. 7-12, 2003, pp.423-430.
[18] Petrov S, Klein D. Discriminative log-linear grammars with atent variables. In Proc. NIPS 2008, Vancouver, Canada, Dec. 8-13, 2008, pp.1-8.
[19] Charniak E. Immediate-head parsing for language models. In Proc. ACL 2001, Tonlouse, France, Jul. 9-11, 2001, pp.129-137.
[20] Joachims T. Text categorization with support vector machine: earning with many relevant features. In Proc. ECML1998, hemnitz, Germany, Apr. 21-23, 1998, pp.137-142.
[21] Moschitti A. Making tree kernels practical for natural lanuage learning. In Proc. EACL 2006, Trento, Italy, Apr. 3-7, 2006, pp.113-120.
[22] Zhang M, Che W X, Zhou G D, Aw A T, Tan C L, Liu T, i S. Semantic role labeling using a grammar-driven convoution tree kernel. IEEE Transaction on Audio, Speech and anguage Processing, 2008, 16(7): 1315-1329.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] Zhu Mingyuan;. Two Congruent Semantics for Prolog with CUT[J]. , 1990, 5(1): 82 -91 .
[2] Wu Xindong;. Inductive Learning[J]. , 1993, 8(2): 22 -36 .
[3] Tang Weiqing; Wen Sili; Liu Shenquan;. An Object-Oriented Model ofUser Interface Generation Tool[J]. , 1994, 9(3): 275 -284 .
[4] Tan Qingping;. A Higher-Order Unification Algorithm for Inductive Types and Dependent Types[J]. , 1997, 12(3): 231 -243 .
[5] Schubert Foo; Siu Cheung Hui;. System Architectural Design for DeliveringVideo Mail over the World-Wide-Web[J]. , 1997, 12(4): 372 -385 .
[6] Tao Renji; Chen Shihua; Chen Xuemei;. FAPKC3: A New Finite Automaton PublicKey Cryptosystem[J]. , 1997, 12(4): 289 -305 .
[7] Zhou Chaochen;. An Overview of Duration Calculus[J]. , 1998, 13(6): 552 .
[8] SUN Yongqiang; LIN Kai; LU Chaojun;. Partial Completion of Equational Theories[J]. , 2000, 15(6): 552 -559 .
[9] Heng Li, Jin-Song Liu, Zhao Xu et al.. Test Data Sets and Evaluation of Gene Prediction Programs on the Rice Genome[J]. , 2005, 20(4): 446 -453 .
[10] Hua Li, Shui-Cheng Yan, and Li-Zhong Peng[1]. Robust Non-Frontal Face Alignment with Edge Based Texture[J]. , 2005, 20(6): 849 -854 .

ISSN 1000-9000(Print)

         1860-4749(Online)
CN 11-2296/TP

 Home
Editorial Board
Author Guidelines
Subscription		 Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
Tel.:86-10-62610746
E-mail: jcst@ict.ac.cn
 
  Copyright ©2015 JCST, All Rights Reserved