›› 2013,Vol. 28 ›› Issue (6): 1117-1126.doi: 10.1007/s11390-013-1402-9

所属专题: Artificial Intelligence and Pattern Recognition

• Special Section on Selected Paper from NPC 2011 • 上一篇    


Hong-Ling Wang (王红玲), Member, CCF, and Guo-Dong Zhou* (周国栋), Senior Member, CCF, Member, ACM, IEEE   

  • 收稿日期:2012-12-10 修回日期:2013-09-18 出版日期:2013-11-05 发布日期:2013-11-05
  • 作者简介:Hong-Ling Wang received the Ph.D. degree in computer application technology from Soochow University, Suzhou, China, in 2009. Currently, she is an associate professor at the university. Her research interests include natural language processing and information extraction. She has been a member of CCF since 2009.

Semantic Role Labeling of Chinese Nominal Predicates with Dependency-Driven Constituent Parse Tree Structure

Hong-Ling Wang (王红玲), Member, CCF, and Guo-Dong Zhou* (周国栋), Senior Member, CCF, Member, ACM, IEEE   

  1. Natural Language Processing Lab, School of Computer Science and Technology, Soochow University, Suzhou 215006, China
  • Received:2012-12-10 Revised:2013-09-18 Online:2013-11-05 Published:2013-11-05
  • Supported by:

    Supported by the National Natural Science Foundation of China under Grant Nos. 61331011 and 61273320, the National High Technology Research and Development 863 Program of China under Grant No. 2012AA011102, and the Natural Science Foundation of Jiangsu Provincial Department of Education under Grant No. 10KJB520016.


Abstract: This paper explores a tree kernel based method for semantic role labeling (SRL) of Chinese nominal predicates via a convolution tree kernel. In particular, a new parse tree representation structure, called dependency-driven constituent parse tree (D-CPT), is proposed to combine the advantages of both constituent and dependence parse trees. This is achieved by directly representing various kinds of dependency relations in a CPT-style structure, which employs dependency relation types instead of phrase labels in CPT (Constituent Parse Tree). In this way, D-CPT not only keeps the dependency relationship information in the dependency parse tree (DPT) structure but also retains the basic hierarchical structure of CPT style. Moreover, several schemes are designed to extract various kinds of necessary information, such as the shortest path between the nominal predicate and the argument candidate, the support verb of the nominal predicate and the head argument modified by the argument candidate, from D-CPT. This largely reduces the noisy information inherent in D-CPT. Finally, a convolution tree kernel is employed to compute the similarity between two parse trees. Besides, we also implement a feature-based method based on D-CPT. Evaluation on Chinese NomBank corpus shows that our tree kernel based method on D-CPT performs significantly better than other tree kernel-based ones and achieves comparable performance with the state-of-the-art feature-based ones. This indicates the effectiveness of the novel D-CPT structure in representing various kinds of dependency relations in a CPT-style structure and our tree kernel based method in exploring the novel D-CPT structure. This also illustrates that the kernel-based methods are competitive and they are complementary with the featurebased methods on SRL.

[1] Surdeanu M, Harabagiu S, Williams J, Aarseth P. Using predicate-argument structures for information extraction. In Proc. the 41st Annual Meeting on Association for Computational Linguistics, July 2003, Vol.1, pp.8-15.

[2] Narayanan S, Harabagiu S. Question answering based on semantic structures. In Proc. the 20th Int. Conf. Computational Linguistics, August 2004, Article No. 693.

[3] Ponzetto S P, Strube M. Semantic role labeling for coreference resolution. In Proc. the 11th EACL, April 2006, pp.143-146.

[4] Persson J, Johansson R, Nugues P. Text categorization using predicate-argument structures. In Proc. the 17th NODALIDA, May 2009, pp.142-149.

[5] Moschitti A, Pighin D, Basili R. Tree kernels for semantic role labeling. Computational Linguistics, 2008, 34(2): 193-224.

[6] Moschitti A. Efficient convolution kernels for dependency and constituent syntactic trees. In Proc. the 17th ECML, September 2006, pp.318-329.

[7] Punyakanok V, Roth D, Yih W. The necessity of syntactic parsing for semantic role labeling. In Proc. the 19th IJCAI, July 30-August 5, 2005, pp.1117-1123.

[8] Moschitti A, Bejan C A. A semantic kernel for predicate argument classification. In Proc. the 8th CoNLL, May 2004, pp.17-24.

[9] Moschitti A. A study on convolution kernels for shallow semantic parsing. In Proc. the 42nd ACL, July 2004, Article No. 335.

[10] Moschitti A, Pighin D, Basili R. Tree kernel engineering in semantic role labeling systems. In Proc. the 11st EACL, April 2006, pp.49-56.

[11] Zhang M, Che W X, Aw A, Tan C L, Zhou G D, Liu T, Li S. A grammar-driven convolution tree kernel for semantic role classification. In Proc. the 45th Annual Meeting of the Association of Computational Linguistics, June 2007, pp.200-207.

[12] Zhou G D, Li J H, Fan J X, Zhu Q M. Tree kernel-based semantic role labeling with enriched parse tree structure. Information Processing and Management, 2011, 47(3): 349-362.

[13] Hacioglu K. Semantic role labeling using dependency trees. In Proc. the 20th COLING, August 2004, Article No. 1273.

[14] Johansson R, Nugues P. Dependency-based semantic role labeling of PropBank. In Proc. the 5th EMNLP, Oct. 2008, pp.69-78.

[15] Collins M, Duffy N. New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perception. In Proc. the 40th Annual Meeting on Association for Computational Linguistics, July 2002, pp.263-270.

[16] Che W X, Zhang M, Liu T et al. A hybrid convolution tree kernel for semantic role labeling. In Proc. the 44th ACL, July 2006, pp.73-80.

[17] Croce D, Moschitti A, Basili R, Palmer M. Verb classification using distributional similarity in syntactic and semantic structures. In Proc. the 50th ACL, July 2012, pp.263-272.

[18] Nguyen T T, Moschitti A, Riccardi G. Convolution kernels on constituent, dependency and sequential structures for relation extraction. In Proc. the 2009 Conf. Empirical Methods in Natural Language Processing, Aug. 2009, Vol.3, pp.13781387.

[19] Croce D, Moschitti A, Basili R. Semantic convolution kernels over dependency trees: Smoothed partial tree kernel. In Proc. the 20th CIKM, October 2011, pp.2013-2016.

[20] Johansson R, Moschitti A. Syntactic and semantic structure for opinion expression detection. In Proc. the 14th CoNLL, July 2010, pp.67-76.

[21] Kong F, Zhou G D, Qian L H et al. Dependency-driven anaphoricity determination for coreference resolution. In Proc. the 23rd Int. Conf. Computational Linguistics, August 2010, pp.599-607.

[22] Sun HL, Jurafsky D. Shallow semantic parsing of Chinese. In Proc. the 2004 NAACL, May 2004, pp.249-256.

[23] Pradhan S, Sun H L, Ward W, Martin H J, Jurafsky D. Parsing arguments of nominalizations in English and Chinese. In Proc. HLT-NAACL, May 2004, pp.141-144.

[24] Xue N W, Palmer M. Annotating the propositions in the Penn Chinese Treebank. In Proc. the 2nd SIGHAN Workshop on Chinese Language Processing, July 2003, Vol.17, pp.47-54.

[25] Xue N W. Annotating the predicate-argument structure of Chinese nominalizations. In Proc. the 2006 LREC, May 2006, pp.1382-1387.

[26] Xue N W. Palmer M. Automatic semantic role labeling for Chinese verbs. In Proc. the 19th IJCAI, July 30-August 5,2005, pp.1160-1165.

[27] Xue N W. Semantic role labeling of nominalized predicates in Chinese. In Proc. the 2006 HLT-NAACL, June 2006, pp.431438.

[28] Xue N W. Labeling Chinese predicates with semantic roles. Computational Linguistics, 2008, 34(2): 225-255.

[29] Li J H, Zhou G D, Zhao H, Zhu Q M, Qian P D. Improving nominal SRL in Chinese language with verbal SRL information and automatic predicate recognition. In Proc. EMNLP, August 2009, Vol.3, pp.1280-1288.

[30] Li S Q, Lu Q, Zhao T J, Liu P Y, Li H J. Combing constituent and dependency syntactic views for Chinese semantic role labeling. In Proc. the 23rd COLING, August 2010, pp.665-673.

[31] Bjørkelund A, Hafdell L, Nugues P. Multilingual semantic role labeling. In Proc. the 13th CoNLL, June 2009, pp.43-48.

[32] Meza-Ruiz I, Riedel S. Multilingual semantic role labeling with Markov logic. In Proc. the 13th CoNLL, June 2009, pp.85-90.
No related articles found!
Full text



No Suggested Reading articles found!
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn