王 鑫,穗志方. 基于依存树距离识别论元的语义角色标注系统[J]. 中文信息学报, 2012, 26(2): 40-46.
WANG Xin, SUI Zhifang. Semantic Role Labeling System Based on Dependency Tree Distance Method for Arguments Identification. , 2012, 26(2): 40-46.
基于依存树距离识别论元的语义角色标注系统
王 鑫,穗志方
北京大学 计算语言学研究所,北京 100871
Semantic Role Labeling System Based on Dependency Tree Distance Method for Arguments Identification
WANG Xin, SUI Zhifang
Institute of Computational Linguistics, Peking University, Beijing 100871, China
Abstract：In research on the semantic role labeling based on dependency, most systems apply machine learning to arguments identification and arguments classification. This paper analyses the characteristics of the dependency tree, and find that arguments distribute in specific area of dependency tree. Therefore, we propose a novel rule based method for the semantic role identification according to the dependency tree distance. The maximal distance from candidate arguments to verb is limited to no more than three. We also obtain best candidate arguments related to the verb. For the gold syntactic dependency tree, this method recognizes 98.5% of arguments on CoNLL 2009 Chinese dataset. Combined with arguments classification based on machine learning, the F measure of the system finally reaches 89.46%, which is a significant improvements compared with the previous work (81.68%). Key wordsargument identification; dependency tree distance based method;semantic role labeling
[1] Hai Zhao, Chunyu Kit. Parsing syntactic and semantic dependencies with two single-stage maximum entropy models[C]//Proceedings of the 12th CoNLL-2008, Manchester, August 2008: 203-207. [2] 王步康,王红玲,袁晓虹,等.基于依存句法分析的中文语义角色标注[J].中文信息学报,2010,24(1): 25-29,47. [3] Sameer Pradhan, Wayne Ward, Kadri Hacioglu, et a1. Shallow Semantic Parsing Using Support Vector Machines[C]//Proceedings of NAACL-HLT 04.2004. [4] Taku Kudo,Yuji Matsumoto. Use of support vector learning for chunk identification [C]//Proceedings of CoNLL-2000 and LLL-2000, Lisbon, Portugal, 2000:142-144. [5] Taku Kudo, Yuji Matsumoto. Chunking with support vector machines[C]//Proceedings of the 2nd Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL-2001). [6] Richard Johansson, Pierre Nugues. Dependency-based syntactic semantic analysis with PropBank and NomBank[C]//Proceedings of the 12th CoNLL-2008, Manchester, August 2008: 183-187. [7] Chih-Jen Lin, Ruby C.Weng, S. Sathiya Keerthi. Trust region Newton method for large-scale logistic regression[C]//Proceedings of the 24 th International Conference on Machine Learning, Corvallis, OR, 2007. [8] Nianwen Xue, Palmer M. Calibrating features for semantic role labeling[C]//Proceedings of EMNLP, Barcelona, Spain, 2004: 88-94. [9] 丁金涛,周国栋,王红玲,等.语义角色标注中有效的识别论元算法研究[J].计算机工程与应用, 2008, 44(18), 153-156. [10] 周国光. 汉语配价语法论略[J].南京师范大学学报:社科版,1994(4):103-106,121. [11] 张育,王红玲,周国栋.基于两种句法分析的语义角色标注比较研究[J]. 计算机应用与软件, 2010, 27(8): 565-573.
2012, Vol. 26 
