汉语复句书读前后语言片段的非分句识别  

Identification of Non-clauses among Language Fragments between Punctuations in Chinese Complex Sentences

作　　者：李琼[1] 

机构地区：[1]华中师范大学国际文化交流学院,湖北武汉430079

出　　处：《安庆师范学院学报（社会科学版）》2010年第1期111-114,119,共5页Journal of Anqing Teachers College(Social Science Edition)

基　　金：华中师范大学"丹桂计划"项目:汉语复句书读前后语言片段的非分句识别

摘　　要：为了建立一个面向中文信息处理的现代汉语复句精加工语料库,我们必须进行非分句语言片段的自动识别工作,目的是把这些语言片段排除在分句层次分析的范围之外。这项工作建立在自动分词和词性标注的基础上,主要分三个阶段进行。To build a contemporary Chinese Complex Sentences Corpus facing Chinese Information Processing, we need to start a research on the automatic identification of Non-clauses among language fragments between punctuations in order that we can exclude the non-clauses when we make level-analyses of complex sentences. This research work,which is on the basis of automatic identification of words and speech tagging, can be divided into three stages.

关 键 词：书读前后非分句语言片段 词性 形式标记 语义 

分 类 号：H109.3[语言文字—汉语]