首页> 外文会议>2010 International Symposium on Intelligence Information Processing and Trusted Computing >The Computing Method of Semantic Relevancy of Clauses in Chinese Compound Sentence
【24h】

The Computing Method of Semantic Relevancy of Clauses in Chinese Compound Sentence

机译:汉语复合句中从句的语义相关性计算方法

获取原文

摘要

The automatic recognition of hierarchy and relationship of Chinese compound sentence is a difficulty in Chinese information processing, and it is even more difficult in two points, one is the hierarchy ascription of non-marked clauses, the other is the confirmation of relevancy of clauses in some causal and coordination marked compound sentences. It uses semantic relevancy theory to solve these problems in this paper. The discussion focuses on three parts: sum up the semantic features which indicate the semantic relevancy between clauses from the syntactic and semantic aspects; confirm the analysis order of features according to the restriction law among features and the statistic result of the occurrence of clausesȁ9; features in corpus; discuss the computing method of the semantic relevancy degree between clauses, and then confirm the hierarchy ascription of clauses according to semantic relevancy degree.
机译:中文复合句的层次结构和关系的自动识别是中文信息处理中的一个难题,这在两点上更加困难,其一是未标记的从句的层次结构归属,其二是确认句子中的从句的相关性一些因果和协调标记的复合句子。本文采用语义相关理论解决了这些问题。讨论主要集中在三个部分:总结语义特征,从句法和语义两个方面指示从句之间的语义相关性;根据特征之间的约束规律和第9条出现的统计结果,确定特征的分析顺序;语料库中的特征;讨论了子句之间语义相关度的计算方法,然后根据语义相关度确定子句的层次结构归属。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号