微信服务号

微信订阅号

2025-4-24- 15
Home > Archive>Volume 22, Issue 2, 2011 >222-232. DOI:10.3724/SP.J.1001.2011.03844
PDF HTML XML Export Cite reminder
Chinese Semantic Role Labeling Based on Feature Combination
Author:
Affiliation:

  • Article
    • | |
  • Metrics
    • |
  • Reference [25]
    • |
  • Related [20]
    • |
  • Cited by [1]
    • | |
  • Comments
    Abstract:

    This paper proposes a semantic role labeling (SRL) approach for the Chinese, based on feature combination and support vector machine (SVM). The approach takes the constituent as the labeling unit. First, this paper defines the basic feature set by selecting the high-performance features of existing parsing-based SRL systems. Then, a statistics-based method is proposed to construct a combined feature set derived from the basic feature set. According to the distribution of combining features in both positive and negative instances, the ratio of between-class to within-class distance is utilized as the measurement of classifying the performance the feature, and then choosing the combining features with high ratios into the combining feature set. Finally, the experimental results show that the feature combination method-based SRL achieved 91.81% F-score on Chinese PropBank (CPB) corpus, nearly 2% higher than the traditional method.

    Reference
    [1] Surdeanu M, Harabagiu S, Williams J, Aarseth P. Using predicate-argument structures for information extraction. In: Hinrichs EW, Roth D, eds. Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL). Stroudsburg: ACL, 2003, 8?15. [doi: 10.3115/1075096.1075098]
    [2] Shen D, Lapata M. Using semantic roles to improve question answering. In: Eisner J, ed. Proc. of the Joint Conf. on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL). Stroudsburg: ACL, 2007. 12?21.
    [3] Bilotti MW, Ogilvie P, Callan J, Nyberg E. Structured retrieval for question answering. In: Kraaij W, de Vries AP, Clarke CLA, Fuhr N, Kando N, eds. Proc. of the 30th Annual Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. New York: ACM, 2007. 351?358. [doi: 10.1145/1277741.1277802]
    [4] Fillmore CJ, Baker CF. Frame semantics for text understanding. In: Proc. of the WordNet and Other Lexical Resources Workshop (NACCL). Stroudsburg: ACL, 2001. 59?63.
    [5] Carreras X, Màrquez L. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In: Dagan I, Gildea D, eds. Proc. of the CoNLL. Stroudsburg: ACL, 2005. 152?164. [doi: 10.1162/0891201053630264]
    [6] Palmer M, Gildea D, Kingsbury P. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 2005, 31(1):71?106.
    [7] Baker CF, Fillmore CJ, Lowe JB. The Berkeley FrameNet project. In: Boitet C, Whitelock P, eds. Proc. of the ACL-Coling. Stroudsburg: ACL, 1998. 86?90. [doi: 10.3115/ 980451.980860]
    [8] Schuler KK. VerbNet: A broad-coverage, comprehensive verb lexicon [Ph.D. Thesis]. Philadelphia: University of Pennsylvania, 2005.
    [9] Xue N, Palmer M. Calibrating features for semantic role labeling. In: Lin D, Wu D, eds. Proc. of the EMNLP. Stroudsburg: ACL, 2004. 88?94.
    [10] Gildea D, Jurafsky D. Automatic labeling of semantic roles. Computational Linguistics, 2002,28(3):245?288. [doi: 10.1162/ 089120102760275983]
    [11] Chen J, Rambow O. Use of deep linguistic features for the recognition and labeling of semantic arguments. In: Lin D, Wu D, eds. Proc. of the EMNLP. 2004. 41?48. [doi: 10.3115/1119355.1119361]
    [12] Pradhan S, Hacioglu K, Krugler V, Ward W, Martin JH, Jurafsky D. Support vector learning for semantic argument classification. Machine Learning Journal, 2005,60(3):11?39. [doi: 10.1007/s10994-005-0912]
    [13] Xue N. Labeling Chinese predicates with semantic roles. Computational Linguistics, 2008,34(2):225?255. [doi: 10.1162/coli.2008. 34.2.225]
    [14] Ding W, Chang B. Improving Chinese semantic role classification with hierarchical feature selection strategy. In: Lapata M, Ng HT, eds. Proc. of the EMNLP. Stroudsburg: ACL, 2008. 324?323.
    [15] Zhao H, Chen WL, Kit C. Semantic dependency parsing of NomBank and PropBank—An efficient integrated approach via a large-scale feature selection. In: Koehn P, Mihalcea R, eds. Proc. of the EMNLP. Stroudsburg: ACL, 2009. 30?39.
    [16] Boxwell SA, Dennis Mehay D, Brew C. Brutus: A semantic role labeling system incorporating CCG, CFG, and dependency features. In: Su KY, ed. Proc. of the ACL-IJCNLP. Stroudsburg: ACL, 2009. 37?45.
    [17] Sun H, Jurafsky D. Shallow semantic parsing of Chinese. In: Hirschberg JB, Dumais S, Marcu D, Roukos S, eds. Proc. of the HLTNAACL. Stroudsburg: ACL, 2004. 249?256.
    [18] Xue N, Palmer M. Automatic semantic role labeling for Chinese verbs. In: Kaelbling LP, Saffiotti A, eds. In: Kaelbling LP, Saffiotti, eds. Proc. of the IJCAI. San Francisco: Morgan Kaufmann Publishers, 2005. 1160?1165.
    [19] Liu T, Che WX, Li S. Semantic role labeling with maximum entropy classifier. Journal of Software, 2007,18(3):565?573 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/18/565.htm [doi: 10.1360/jos180565]
    [20] Wang HL. Research on feature-based semantic role labeling for English and Chinese [Ph.D. Thesis]. Suzhou: Soochow University, 2008 (in Chinese with English abstract).
    [21] Che WX. Kernel-Based semantic role labeling [Ph.D. Thesis]. Harbin: Harbin Institute of Technology, 2008 (in Chinese with English abstract).
    [22] Liu HJ, Che WX, Liu T. Feature engineering for Chinese semantic role labeling. Journal of Chinese Information Processing, 2007, 21(2):75?80 (in Chinese with English abstract).
    [23] Ding JT, Wang HL, Zhou GD, Zhu QM, Qian PD. On optimized combination of features in semantic role labeling. Computer Applications and Software, 2009,26(5):17?21 (in Chinese with English abstract).
    [24] Vapnik VN. The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995.
    [25] Joachims T. Making Large-Scale SVM Learning Practical. In: Sch?lkopf B, Burges C, Smola A, eds. Advances in Kernel Methods?Support Vector Learning. Cambridge: MIT Press, 1999.
    Comments
    Comments
    分享到微博
    Submit
Get Citation

李世奇,赵铁军,李晗静,刘鹏远,刘水.基于特征组合的中文语义角色标注.软件学报,2011,22(2):222-232

Copy
Share
Article Metrics
  • Abstract:6604
  • PDF: 8638
  • HTML: 0
  • Cited by: 0
History
  • Received:October 29,2009
  • Revised:January 20,2010
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2038111Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063