J4 ›› 2009, Vol. 47 ›› Issue (4): 769-776.

• 计算机科学 • 上一篇    下一篇

基于最优化控制模型的文本主题域划分

王小芳1, 王瑞芳2, 张树功1   

  1. . 吉林大学 数学研究所, 长春 130012|2. 大连大学 信息工程学院, 辽宁 大连 116622
  • 收稿日期:2009-02-17 出版日期:2009-07-26 发布日期:2009-08-24
  • 通讯作者: 张树功 E-mail:sgzh@mail.jlu.edu.cn.

Text Subtopicfield Segmentation Based on Optimal Control Model

WANG Xiaofang1, WANG Ruifang2, 1   

  1. 1. Institute of Mathematics, Jilin University, Changchun 130012, China;2. College of Information Engineering, Dalian University, Dalian 116622, Liaoning Province, China
  • Received:2009-02-17 Online:2009-07-26 Published:2009-08-24
  • Contact: ZHANG Shugong E-mail:sgzh@mail.jlu.edu.cn.

摘要:

提出一种基于最优化控制模型的文本主题域划分方法, 采用主题域内距离、 主题域间距离、 主题域内夹角和主题域间夹角等相关要素, 构建了最优化模型的目标函数, 进而通过对模型求解得到文本主题域的最优划分模式. 该方法为全局最优化方法, 与具体的应用领域无关, 具有较高的普适性. 实验结果表明, 在算法适用性、 F1评价和Window Diff评价上, 该算法均优于其他相关算法.

关键词: 主题域划分, 主题域内距离, 主题域间距离, 主题域内夹角, 主题域间夹角

Abstract:

A subtopicfield segmentation technique based on the optimal control model was proposed, the object function of the optimal control model was constructed by the withinsubtopicfield distance, the betweensubtopicfield distance, the withinsubtopicfield angle and the betweensubtopicfield angle. By solving the optimal control model, optimal subtopicfield segmentation is obtained. The method independent of specific application is a global optimal method. The experiments show that this method is better than other methods in applicability, F1 measure and Window Diff measure.

Key words: subtopicfield segmentation, withinsubtopicfield distance, betweensubtopicfield distance, withinsubtopicfield angle, betweensubtopicfield angle

中图分类号: 

  • TP391