北京大学学报(自然科学版)

副词“都”用法自动识别研究

张静杰,昝红英   

  1. 郑州大学信息工程学院, 郑州 450001;
  • 收稿日期:2012-05-28 出版日期:2013-01-20 发布日期:2013-01-20

Automatic Recognition Research on Chinese Adverb DOU’s Usages

ZHANG Jingjie, ZAN Hongying   

  1. School of Information Engineering, Zhengzhou University, Zhengzhou 450001;
  • Received:2012-05-28 Online:2013-01-20 Published:2013-01-20

摘要: 首先对副词“都”分别进行基于规则和基于统计两种方法的用法自动识别研究, 并具体分析它们的优点和不足, 然后尝试了规则与统计相结合的方法。3种方法的准确率分别为82%, 89.62%和98.54%, 实验数据表明, 采用规则和统计相结合的方法使副词“都”用法的自动识别取得较好的效果。

关键词: 自然语言处理, 用法规则, 条件随机场, 自动识别,

Abstract: The authors recognized the adverb DOU’s usages with two methods, rule-based and statistics-based, and analyzed theirs advantages and disadvantages, respectively. And then, the methods of rule-based and statistical- based were combined. The accuracies of these three methods are 82%, 89.62% and 98.54%. The experiments show that combination method of rule-based and statistical-based is more effective in automatically recognizing of adverb DOU’s usages.

Key words: natural language process, usage rule, conditional random fields, automatic identification, DOU

中图分类号: