在斯坦福基础依存句法规范的基础上,该文研制了汉语增强依存句法规范,主要贡献在于: 介词和连词的增强、并列项的传播、句式转换和特殊句式的增强。此外,该文提供了基于Python的汉语增强依存句法转换的转换器,以及将句子从基础依存句法树通过所提规范解析成依存图的Web演示。最后,该文探索了增强依存句法的实际应用,并以搭配抽取和信息抽取为例进行相关讨论。
Abstract
Based on the Stanford Basic Dependency Syntax standards, this paper developed a guidelines of enhanced dependency syntax for Chinese. The main contributions include: prepositions and conjunctions, parallel structures, syntactic alternations and special syntactic. Furthermore, this paper provides a converter for Chinese Enhanced Dependency transformation by Python, and a web-based demo that parses sentences into dependency graphs through universal syntactic dependencies and the specification of this paper. Lastly, the paper explores practical applications of augmented dependency syntax such as collocation extraction and information extraction.
关键词
依存句法 /
汉语增强依存句法 /
自动转换
{{custom_keyword}} /
Key words
dependency syntax /
enhanced dependencies in Chinese /
automatic transformation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李正华. 汉语依存句法分析关键技术研究[D]. 哈尔滨: 哈尔滨工业大学博士学位论文, 2013.
[2] DE MARNEFFE M C, MANNING C D. Stanford typed depndencies manual[R]. Stanford University, 2008.
[3] NIVRE J, DE MARNEFFE M C, GINTER F, et al. Univers-al dependencies v1: A multilingual treebank collection[C]//Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016: 1659-1666.
[4] SCHUSTER S, MANNING C D. Enhanced English universal dependencies: An improved representation for natural language understanding tasks[C]//Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016: 2371-2378.
[5] NIVRE J, DE MARNEFFE M C, GINTER F, et al. Universal dependencies v2: An evergrowing multilingual treebank collection[C]//Proceedings of the 10th International Conference on Language Resources and Evaluation, 2020: 4034-4043.
[6] CANDITO M, GUILLAUME B, PERRIER G, et al. Enhanced UD dependencies with neutralized diathesis alternation[C]//Proceedings of the Depling 4th International Conference on Dependency Linguistics, 2017.
[7] NIVRE J, MARONGIU P, GINTER F, et al. Enhancing universal dependency treebanks: A case study[C]//Proceedings of the 2nd Workshop on Universal Dependencies, 2018: 102-107.
[8] TIKTINSKY A, GOLDBERG Y, TSARFATY R. Pybart: Evidence-based syntactic transformations for IE[C]//Proceedings of the 58th Annual Meeting of ACL, 2020: 47-55.
[9] 刘丹青. 汉语中的框式介词[J]. 当代语言学, 2002, 4(4): 241-253.
[10] 年玉萍. 谈谈兼语句[J]. 延安教育学院学报, 2003, 17(1): 40-42.
[11] 刘月华, 潘文娱, 故韡. 实用现代汉语语法(增订本)[M]. 北京: 商务印书馆, 2001.
[12] 邵艳秋, 申资卓, 刘世军. 基于依存搭配抽取技术的平面媒体语言监测研究[J]. 山西大学学报(自然科学版), 2019, 42(3): 526-533.
[13] 项威, 王邦. 中文事件抽取研究综述[J]. 计算机技术与发展, 2020, 30(2): 1-6.
[14] 张素香. 信息抽取中关键技术的研究[D]. 北京: 北京邮电大学硕士学位论文, 2007.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家语委项目(ZDI135-131);中外语言交流合作中心《国际中文教育中文水平等级标准》教学资源建设项目(YHJC21YB-129);中央高校基本科研业务费(北京语言大学梧桐创新平台,21PT04)
{{custom_fund}}
PDF(1426 KB)
