TCBPLK: A NEW METHOD OF TEXT CATEGORIZATION

摘要：

This paper presents a new text categorization method based on P-L theory and Kohonen network, which called TCBPLK method.The Kohonen network is applied to realizing text categorization, which has a defect of too slowly speed of training.To text vector of high dimension, the defect is more obvious.Even the result of text categorization can not be acquired.The new method establishes vector space model of term weight by the theory of P-L, which enhances the function of the words from the viewpoint of categorization effect, and decreases the dimension of vector through eliminating redundant features.Experimental results confirm that TCBPLK method decreases the number of vector, and enhances the generalization and precision of text categorization.

关键词： Text categorization P-L theory Kohonen network Vector space model

作者: JIAN-SUO XU

作者单位: School of Economy, Beijing University, Beijing, 100871, China

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 3889-3892

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）