基于模板的汉语复句改写方法研究  

Study on paraphrasing method of Chinese complex sentences based on templates

作　　者：林燕芬[1] 郜炎峰 王忠建[1] 

机构地区：[1]哈尔滨商业大学计算机与信息工程学院,哈尔滨150028

出　　处：《哈尔滨商业大学学报（自然科学版）》2016年第5期558-562,共5页Journal of Harbin University of Commerce：Natural Sciences Edition

基　　金：黑龙江省自然科学基金(F201243);黑龙江省教育厅科研项目(12511127)

摘　　要：在汉语简单句改写的基础上,提出了基于模板的汉语复句的改写方法.通过对复句分类以及复句的语法结构分析,进而抽取复句的改写模板.在构筑以关联词为核心的复句语料库,对语料库进行分词、词性标注等处理的基础上,通过大量的相似度计算实验,确定了待改写句与其改写模板之间的阈值,进行的改写实验结果表明复句模板覆盖率为40.20%,改写正确率62.61%.Based on the paraphrasing of simple sentences in Chinese,a method to paraphrase Chinese complex sentences based on template was proposed. Through analyzing classification and grammatical structure of the complex sentences,the paraphrasing template of complex sentences was extracted. By building the complex sentences corpus with associated words as a core,word segmentation and part of speech tagging,making massive similarity calculation experiments,which determines the threshold between paraphrasing sentences and paraphrasing templates. The experimental results showed that paraphrasing template coverage rate was40. 20%,and the paraphrasing correct rate was 62. 61%.

关 键 词：复句 关联词 语料库 改写模板 

分 类 号：H146[语言文字—汉语]