基于多元判别分析的文本分割模型-软件学报.pdf

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software, Vol.18, No.3, March 2007, pp .555−564 http://www.j DOI: 10. 1360/jos1 80555 Tel/Fax : +86-10 © 2007 by Journal of Software. All rights reserved. ∗ 基于多元判别分析的文本分割模型 + 朱靖波 , 叶 娜, 罗海涛 (东北大学 计算机软件研究所,辽宁 沈阳 110004) Text Segmentation Model Based on Multiple Discriminant Analysis + ZHU Jing-Bo , YE Na, LUO Hai-Tao (Institute of Computer Software and Theory, Northeastern University, Shenyang 110004, China) + Corresponding author: Phn: +86-24 E-mail: zhujingbo@, Zhu JB, Ye N, Luo HT. Text segmentation model based on multiple discriminant analysis. Journal of Software, 2007,18(3):555−564. /1000-9825/18/555.htm Abstract: This paper proposes a new domain-independent statistical model. In this model, four multiple discriminant analysis (MDA) criterion functions are defined and used to achieve global optimization in finding the best segmentation by means of the smallest within-segment distance, the largest between-segment distance and segment length. To alleviate the high computational complexity problem introduced by the new model, genetic algorithms (GAs) are used. Comparative experimental results show that the methods based on MDA criterion functions have achieved higher Pµ than that of TextTiling and Dotplotting algorithms. Key words: text segmentation; multiple discriminant analysis; within-segment distance; between-segment distance; segment unit length; genetic algorithm 摘 要: 提出了一种独立于具体领域的文本线性分割统计模型,其中采用多元判别分析方法定义了 4