利用配价信息的语义角色标注

doi:10.3969/j.issn.0372-2112.2017.10.031

电子学报 ›› 2017, Vol. 45 ›› Issue (10): 2533-2539.DOI: 10.3969/j.issn.0372-2112.2017.10.031

利用配价信息的语义角色标注

袁里驰

江西财经大学信息管理学院, 江西南昌 330013

收稿日期:2015-07-29 修回日期:2015-09-29 出版日期:2017-10-25
- 作者简介:
- 袁里驰,男,博士,1973年5月出生于湖南邵阳,江西财经大学信息管理学院计算机科学与技术系副教授,硕士生导师.研究方向为自然语言处理.E-mail:yuanlichi@sohu.com
- 基金资助:
- 国家自然科学基金 (No.61562034，No.61262035）; 江西省科技支撑计划 (No.20151BBE50082）; 江西省自然科学基金 (No.20142BAB207028）

Semantic Role Labeling Utilizing Valence Information

YUAN Li-chi

School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, Jiangxi 330013, China

Received:2015-07-29 Revised:2015-09-29 Online:2017-10-25 Published:2017-10-25

摘要/Abstract

摘要： 语义角色标注是一种浅层语义分析.现有的汉语语义分析方法和语义角色标注体系没有结合汉语的特点并有效刻画出汉语的本质特性，导致目前汉语语义角色标注性能与英语相比相差较大.在汉语中，配价结构可以较好地刻画汉语句子的句法结构和语义构成关系，因此，我们在考察配价语法的基础上适当修改了语义角色标注体系并将谓词本身的配价信息融入语义角色标注.实验结果表明，配价信息的使用能够较大幅度提高动名词性谓词的语义角色标注性能：基于正确句法树和正确谓词识别，动词性谓词的SRL性能F1值达到93.69%；名词性谓词的SRL性能F1值达到79.23% ；均优于目前国内外的同类系统.

关键词: 配价结构, 动词性谓词, 名词性谓词, 语义角色标注

Abstract: Semantic roles labeling is a kind of shallow semantic analysis.Existing Chinese semantic analysis methods and semantic roles labeling systems do not effectively characterize Chinese essential features,and it causes the currently larger difference between Chinese SRL systems and English SRL systems.Valence structures can better characterize syntactic structures and semantic constitution relations of Chinese sentences,so we appropriately modified the semantic roles labeling systems and incorporated the valence information of predicates into semantic roles labeling.Experimental results show that proper use of valence information significantly improves the performance of semantic roles labeling system:the verbal SRL approach achieves the performance of 93.69% in F1-measure and the nominal SRL approach achieves the performance of 79.23% in F1-measure on golden parse trees and golden predicates,and all outperform the state-of-the-art SRL systems.

Key words: valence structure, verbal predicates, nominal predicates, semantic role labeling

中图分类号:

TP391.1

袁里驰. 利用配价信息的语义角色标注[J]. 电子学报, 2017, 45(10): 2533-2539.

YUAN Li-chi. Semantic Role Labeling Utilizing Valence Information[J]. Acta Electronica Sinica, 2017, 45(10): 2533-2539.

参考文献

[1] S Narayanan,S Harabagiu.Question answering based on semantic structures[A].Proceedings of the 20th international conference on Computational Linguistics[C].Stroudsburg,PA,USA,2004.693-701.
[2] D K Wu,P Fung.Can semantic role labeling improve SMT?[A].Proceedings of the 13th Annual Meeting of the European Association for Machine Translation[C].Barcelona,2009.218-225.
[3] M Surdeanu,S Harabagiu,J Williams,P Aarseth.Using predicate-argument structures for information extraction[A].Proceedings of the 41st Annual Meeting on Association for Computational Linguistics[C].Sapporo,2003.8-15.
[4] XUE Nian-wen.Labeling Chinese predicates with semantic roles[J].Computational Linguistics,2008,34(2):225-255.
[5] 李军辉.中文句法语义分析及其联合学习机制研究[D].苏州,苏州大学,2010.64-103. Li Jun-Hui.Research on joint syntactic and semantic parsing for Chinese[D].Suzhou,Soochow University,2010.64-103.(in Chinese)
[6] 李军辉,周国栋,朱巧明,钱培德.中文名词性谓词语义角色标注[J].软件学报,2011,22(8):1725-1737. Li Jun-hui,Zhou Guo-dong,Zhu Qiao-ming,Qian Pei-de.Semantic role labeling in Chinese language for nominal predicates[J].Journal of Software,2011,22(8):1725-1737.(in Chinese)
[7] 吴方磊,李军辉,朱巧明,李培峰.基于树核函数的中文语义角色分类研究[J].中文信息学报,2011,25(3):51-58. Wu Fang-lei,Li Jun-hui,Zhu Qiao-ming,Li Pei-feng.Tree kernel-based semantic role classification in Chinese language[J].Journal of Chinese Information Processing,2011,25(3):51-58.(in Chinese)
[8] 李业刚,孙福振,李鉴柏,吕新宇.语义角色标注研究综述[J].山东理工大学学报(自然科学版),2011,25(6):19-24. Li Ye-gang,Sun Fu-zhen,Li Jian-bai,Lu Xin-yu.A survey on semantic role labeling[J].Journal of Shandong University of Technology(Natural Science Edition),2011,25(6):19-24.(in Chinese)
[9] 庄成龙,钱龙华,周国栋.基于树核函数的实体语义关系抽取方法研究[J].中文信息学报,2009,23(1):3-8. Zhuang Cheng-long,Qian Long-hua,Zhou Guo-don.Research on tree kernel-based entity semantic relation extraction[J].Journal of Chinese Information Processing,2009,23(1):3-8.(in Chinese)
[10] 王红玲,袁晓虹,王步康,周国栋.依存关系上的中文名词性谓词识别研究[J].计算机工程与应用,2011,47(20):113-116. Wang Hong-ling,Yuan Xiao-hong,Wang Bu-kang,Zhou Guo-dong.Nominal predicate identification for dependency-based Chinese semantic role labeling[J].Computer Engineering and Applications,2011,47(20):113-116.(in Chinese)
[11] 王步康,王红玲,袁晓虹,周国栋.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):25-30. Wang Bu-kang,Wang Hong-ling,Yuan Xiao-hong,Zhou Guo-dong.Chinese dependency parse based semantic role labeling[J].Journal of Chinese Information Processing,2010,24(1):25-30.(in Chinese)
[12] 尹晓丽.通用语义角色自动标注研究[J].长春工业大学学报(自然科学版),2012,33(2):171-175. Yin Xiao-li.An automatic general semantic role labeling system[J].Journal of Changchun University of Technology(Natural Science Edition),2012,33(2):171-175.(in Chinese)
[13] 王智强,李茹,阴志洲,刘海静,李双红.基于依存特征的汉语框架语义角色自动标注[J].中文信息学报,2013,27(2):34-40. Wang Zhi-qiang,Li Ru,Yin Zhi-zhou,Liu Hai-jing,Li Shuang-hong.Automatic labeling of Chinese frame semantic roles based on dependency features[J].Journal of Chinese Information Processing,2013,27(2):34-40.(in Chinese)
[14] 张秀龙,李新德,戴先中.基于组块分析的路径自然语言语义角色标注方法[J].东南大学学报(自然科学版),2012,42(s1):127-131. Zhang Xiu-long,Li Xin-de,Dai Xian-zhong.Semantic role labeling method for route natural language based on chunk parsing[J].Journal of Southeast University (Natural Science Edition),2012,42(s1):127-131.(in Chinese)
[15] 徐靖,李军辉,朱巧明,李培峰.基于短语和依存句法结构的中文语义角色标注[J].计算机工程,2011,37(24):169-172. Xu Jing,Li Jun-hui,Zhu Qiao-ming,Li Pei-feng.Chinese semantic role labeling based on phrase and dependency syntactic structure[J].Computer Engineering,2011,37(24):169-172.(in Chinese)
[16] C F Biker,C J Fillmore,J B Lowe.The Berkeley FrameNet project[A].Proceedings of the 17th international conference on Computational linguistics[C].Montreal,1998.86-90.
[17] M Palmer,D Gildea,P Kingsbury.The proposition bank:an annotated corpus of semantic roles[J].Computational Linguistics,2005,31(1):71-106.
[18] M P Marcus,M A Marcinkiewicz,B Santorini.Building a large annotated corpus of English:the Penn treebank[J].Computational Linguistics,1993,19(2):313-330.
[19] A Meyers,R Reeves,C Macleod,R Szekely,V Zielinska, B Young,R Grishman.Annotating noun argument structure for NomBank[A].Proceedings of the International Conference on Language Resources and Evaluation[C].Lisbon,2004.803-806.
[20] N W Xue,M Palmer.Annotating the propositions in the Penn Chinese treebank[A].Proceedings of the 2nd SIGHAN Workshop on Chinese Language Processing[C].Sapporo,2003.47-54.
[21] Xue NW.Annotating the predicate-argument structure of Chinese nominalizations[A].Proceedings of the International Conference on Language Resources and Evaluation[C].Genoa:2006.1382-1387.
[22] 刘金凤.面向自然语言处理的汉语句子语义知识库构建研究[D].烟台,鲁东大学,2009:27-41. Liu Jin-feng.Research on the construction of a NLP-oriented Chinese sentence semantic knowledge database[D].Yantai, Ludong University,2009:27-41.(in Chinese)
[23] 袁里驰.基于配价结构和语义依存关系的句法分析统计模型[J].电子学报,2013,41(10):2029-2034. Yuan Li-chi.A statistical parsing model based on valence Structure and semantic dependency[J].Acta Electronica Sinica,2013,41(10):2029-2034.(in Chinese)
[24] 袁毓林.汉语配价语法研究[M].北京,商务印书馆,2010.55-170. Yuan Yu-lin.The Study of Chinese Valence Grammars[M].Beijing:Commercial Press,2010.55-170.(in Chinese)
[25] Collins M.Head-Driven Statistical Models for Natural Language Parsing[J].Computational Linguistics,2003,29(4):589-637.

利用配价信息的语义角色标注

Semantic Role Labeling Utilizing Valence Information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

[1]	张志昌, 曾扬扬, 庞雅丽. 融合语义角色和自注意力机制的中文文本蕴含识别[J]. 电子学报, 2020, 48(11): 2162-2169.
[2]	袁里驰. 基于配价结构和语义依存关系的句法分析统计模型[J]. 电子学报, 2013, 41(10): 2029-2034.