基于概念学习的过滤模板获取方法  

Method of Filtering Profile Extraction Based on Concept Learning

作　　者：朱祥玉[1] 侯德文[1] 

机构地区：[1]山东师范大学信息管理学院,山东济南250014

出　　处：《计算机技术与发展》2006年第5期53-55,共3页Computer Technology and Development

基　　金：山东省中青年科学家奖励基金(03BS009)

摘　　要：基于内容的文本过滤关键在于建立有效的过滤模板。一种高效的过滤模板可以降低整个文本过滤系统对机器学习机制的要求,提高系统的过滤效率。提出了一种基于概念学习的过滤模板获取方法。该方法结合处理文本特征项的需要改进了概念学习方法中的寻找极大特殊假设算法,并应用新的算法从给定的少量训练文本中提取用户过滤模板。实验结果表明,与直接使用主题描述作为过滤模板的方法相比,较大地提高了过滤精度,可以达到比较令人满意的过滤效果。The key to content - based text filtering consists in constructing an effective filtering profile. An effective filtering profile can debase the request from the whole text filtering system to the machine learning mechanism and improve filtering efficiency of system. This paper brings forward a method for constructing filtering profile The method improves the find - maximum - special - supposion algorithm in the methods of concept learning by combining the need for deaing with the text feature items and constructs filtering profile from a few training texts by using the new algorithm. The result of experiments shows that, compared with the method which uses the subject- description as filtering profile straight, this method improves filtering precision markedly,and it can obtain the satisfying filtering purpose.

关 键 词：文本过滤 过滤模板 概念学习 TFFind—S算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]