计算机应用 ›› 2013, Vol. 33 ›› Issue (06): 1582-1586.DOI: 10.3724/SP.J.1087.2013.01582

• 人工智能 • 上一篇    下一篇

基于依存分析的中文时间表达式类型判定

肖升1,2,何炎祥2,李勇帆1   

  1. 1. 湖南第一师范学院 信息科学与工程系,长沙 410205
    2. 武汉大学 计算机学院, 武汉 430079
  • 收稿日期:2012-12-23 修回日期:2013-02-13 出版日期:2013-06-01 发布日期:2013-06-05
  • 通讯作者: 肖升
  • 作者简介:肖升(1980-),男,湖南武冈人,副教授,博士,主要研究方向:中文信息处理;何炎祥(1952-),男,湖北应城人,教授,博士生导师,博士,CCF高级会员,主要研究方向:可信软件、自然语言处理;李勇帆(1959-),男,湖南邵东人,教授,主要研究方向:自然人机交互。
  • 基金资助:

    国家自然科学基金资助项目(60873095);湖南省高校科技创新团队支持计划项目(湘教通[2010]212号);湖南省科技厅高新计划项目(2010GK3049)

Classification of Chinese time expressions based on dependency parsing

XIAO Sheng1,2,HE Yanxiang2,LI Yongfan1   

  1. 1. Department of Information Science and Engineering, Hunan First Normal College, Changsha Hunan 410205,China
    2. School of Computer Science, Wuhan University, Wuhan Hubei 430079, China
  • Received:2012-12-23 Revised:2013-02-13 Online:2013-06-05 Published:2013-06-01
  • Contact: XIAO Sheng

摘要: 某些“基数词+时间单位词”组成的中文时间表达式在不同语境中可能表现为时点式,也可能表现为时段式。为自动判定中文时间表达式的类型,提出一种基于依存分析的判定方法。该方法首先借助依存分析考察中文时间表达式在句中所受的句法约束,然后将这些约束转化为具有可计算性的依存规则,最后利用依存规则对中文时间表达式的类型进行判定。实验结果显示,在此方法中,时间表达式确认的正确率、召回率、F值分别达到82.3%、88.1%和85.1%;时间表达式类型判定的正确率、召回率、F值分别达到77.1%、82.5%和79.7%。

关键词: 中文时间表达式, 时点式, 时段式, 依存分析, 类型判定

Abstract: Some Chinese time expressions consisting of "cardinal+time unit word" may be time point expressions or time slot expressions in different context. An approach of classification of Chinese time expressions based on dependency parsing was proposed, for the purpose of automatic classification of Chinese time expressions. First some syntactic constraints of Chinese time expressions in sentences were found with the help of dependency parsing. Then some computable dependency rules were extracted from those syntactic constraints. Finally the classification of Chinese time expressions was executed using dependency rules. The experimental results show that in this approach the precision, recall, F-Measure of the confirmation are 82.3%, 88.1%, 85.1%; and the precision, recall, F-Measure of the classification are 77.1%, 82.5%, 79.7%.

Key words: Chinese time expression, time point expression, time slot expression, dependency parsing, classification

中图分类号: