汉语篇章连接词识别与分类

北京大学学报（自然科学版）

汉语篇章连接词识别与分类

李艳翠^1,2,孙静¹,周国栋¹

1. 苏州大学计算机科学与技术学院, 苏州 215006; 2. 河南科技学院信息工程学院, 新乡 453003;

收稿日期:2014-06-29 出版日期:2015-03-20 发布日期:2015-03-20

Automatic Recognition and Classification on Chinese Discourse Connective

LI Yancui^1,2, SUN Jing¹, ZHOU Guodong¹

1. Department of Computer Science and Technology, Soochow University, Suzhou 215006; 2. School of Information Engineering, Henan Institute of Science and Technology, Xinxiang 453003;

Received:2014-06-29 Online:2015-03-20 Published:2015-03-20

摘要/Abstract

摘要： 基于自建的汉语篇章结构语料库以及语料库中连接词和连接词关系类别的标注, 抽取自动句法树和标准句法树的句法、词法和位置特征, 利用有监督的方法进行连接词识别和分类。实验结果表明, 连接词识别的F1值为69.2%, 连接词自动识别并分类的总正确率为89.1%。

关键词: 连接词识别, 连接词分类, 汉语篇章

Abstract: Based on the annotation of discourse connective in Chinese Discourse Treebank, especially the annotation of the connective and its relation classification. The authors extract syntax, lexical and position features of automatic syntax tree and standard syntax tree, and use supervised method to recognize and classify connective. Experimental results show that connective recognition F1-measure is 69.2%, and connective classification accuracy is 89.1%.

Key words: connective recognition, connective classification, Chinese discourse

中图分类号:

TP391

李艳翠,孙静,周国栋. 汉语篇章连接词识别与分类[J]. 北京大学学报（自然科学版）.

LI Yancui,SUN Jing,ZHOU Guodong. Automatic Recognition and Classification on Chinese Discourse Connective[J]. Acta Scientiarum Naturalium Universitatis Pekinensis.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://xbna.pku.edu.cn/CN/

https://xbna.pku.edu.cn/CN/Y2015/V51/I2/307