汉语是一种语序灵活的语言,句子变式很多,基于传统依存树的投射现象还不能很好解决某些句式的语义理解问题。文章以10000个句子的汉语语义依存图库为基础,验证并明确了汉语非投射现象的客观存在性,考察了汉语句子中存在的非投射现象,并从语言学和句子深层语义理解的角度对非投射现象进行了归纳和解释。文章总结了7类出现非投射现象的情况,包括小句宾语句、比较句、主谓谓语句、紧缩复句、代词、动补谓语句以及注释短语或复句。这对于自动语义依存标注有重要的指导作用。
Abstract
Chinese is flexible in the word order, with different sentences for the same meaning. Projective phenomenon, based on the traditional dependency tree, cannot solve some Chinese phenomenon perfectly. This paper, demonstrates and analyses the existence of non-projective phenomenon in Chinese from a semantic dependency graph database with 10 thousand Chinese sentences. To give an induction and explanation in term of linguistics and deep understanding of semantics, the paper summarizes 7 situations in which the non-projective phenomenon exists, including sentences with sentences used as object, comparative sentences, sentences with sentences used as predicate, sentences with two or more events, pronouns, verb and complement phrases used as predicate and note phrases or sentences. This is of substantial significance to the automatic semantic dependency tagging.
关键词
语义分析 /
语义依存 /
非投射结构 /
依存图
{{custom_keyword}} /
Key words
semantic analysis /
semantic dependency /
non-projective structure /
dependency graph
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Min Zhang, Wanxiang Che, Guodong Zhou,et al. Semantic Role Labeling Using a Grammar-Driven Convolution Tree Kemel[J]. IEEE Transactions on Audio,Speech and Language Processing. 2008,16(7): 1315-1329.
[2] Wanxiang Che, Min Zhang, Ai Ti Aw, et al. Using a Hybrid Convolution Tree Kernel for Semantic Role Labeling [J]. ACM Transactions on Asian Language Information Processing.2008,7(4): 1-23.
[3] 丁伟伟,常宝宝.基于语义组块分析的汉语语义角色标注[J]. 中文信息学报,2009,23(5): 53-61,74.
[4] 陈菜芳.中文语义角色标注研究概述[J]. 文教资料, 2012,(27): 139-140.
[5] 尤昉,李涓子,王作英. 基于语义依存关系的汉语语料库的构建[J]. 中文信息学报,2003,17(1): 46-53.
[6] 陈波,姬东鸿,吕晨.基于特征结构的汉语连动句语义标注研究[J]. 中文信息学报,2013,27(5): 60-66,74.
[7] 陈波,姬东鸿,吕晨.基于特征结构的汉语主谓谓语句语义标注研究[J]. 中文信息学报,2012,26(3): 22-26,32.
[8] Weiwei Sun, Yantao Du, Xin Kou, et al. Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing[C]//Proceedings of the Association for Computational Linguistics.2014,446-456.
[9] 王跃龙,姬东鸿.汉语依存图库建设研究[C]. 萧国政,何炎祥,孙茂松.《中国计算技术与语言问题研究--第七届中文信息处理国际会议论文集》.北京: 电子工业出版社,2007: 251-256.
[10] Robinson,J.J.Dependency structures and transformation rules[J].Language,1970, 46(2):259-285.
[11] Ryan McDonald, Fernando Pereira, KirilRibarov,JanHajicˇ. Non-projective Dependency Parsing using Spanning Tree Algorithms[C]//Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing.2005:523-530.
[12] 邵艳秋,邱立坤,梁春霞等.中文语义依存树库构建及自动分析技术[C].孙茂松,陈群秀.《中国计算语言学研究前沿进展(2009-2011)》.北京: 清华大学出版社,2011: 228-233.
[13] 鲁川. 汉语语法的意合网络[M].北京: 商务印书馆,2001: 64-65.
[14] 范晓. 汉语的句子类型[M].太原: 书海出版社,1998: 58-59,182.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61170144);中央高校基本科研业务费专项基金(14YJ110001);北京语言大学2014年中青年学术骨干支持计划
{{custom_fund}}
PDF(3454 KB)
