基于语义依存图库的兼语句句模研究  

Study on Semantic Sentence Patterns of Chinese Pivotal Sentence Based on Semantic Dependency Graph

作　　者：郑丽娟[1] 邵艳秋[1] 

机构地区：[1]北京语言大学信息科学学院,北京100083

出　　处：《中文信息学报》2015年第6期30-37,共8页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61170144);国家语委十二五科研规划重点项目(ZDI125-41);2014年度北京语言大学中青年学术骨干支持计划;北京语言大学研究生创新基金(中央高校基本科研业务费专项资金)(15YCX102)

摘　　要：句子语义分析是语言研究深入发展的客观要求,也是当前制约语言信息处理技术深度应用的主要因素。在探索深层语义分析方法的基础上,该文根据汉语的特点,提出了一整套语义依存图的构建方法,并建立了一个包含30 000个句子的语义依存图库。以兼语句为重点研究对象,该文研究了语料库中所有纯粹的兼语句所对应的句模情况,进而试图构建基于语义依存图的句模系统,总结句型和句模的映射规则,从而为更好的建立语义自动分析模型提供相应的知识库。Semantic analysis of sentences is essential to language study, and it is also the major bottleneck restricting the large-scale application of language information technology at present. Based on the study of deep semantics anal- ysis methods, we propose a new semantic analysis method-Semantic Dependency Graph, and construct a corpus consisting of 30,000 sentences. Furthermore, we make a study on the semantic sentence patterns of pure pivotal sen- tences in the corpus, and try to construct the system of semantic sentence patterns based on semantic dependency graph. We also summarize corresponding relations between sentence patterns and semantic sentence patterns to pro- vide the automatic semantic parsing system with a corresponding knowledge base.

关 键 词：句模 语义分析 语义依存图 兼语句 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]