基于概念扩充的文本过滤模型  

A Text Filtering Module Based on Concept-expanded

作　　者：尤文建[1] 李绍滋[1] 李堂秋[1] 

机构地区：[1]厦门大学计算机系,厦门361005

出　　处：《计算机工程与应用》2003年第25期74-77,共4页Computer Engineering and Applications

基　　金：国家863高技术研究发展计划项目(编号:2001AA114110);福建省科技计划重点项目(编号:2001H023)

摘　　要：该文在介绍文本过滤的背景及向量空间模型的同时,提出了基于语义词典对用户模板进行扩充的文本过滤模型,该模型首先对文本进行分析,把文本表示成向量空间中的向量形式,在形成用户初始模板之后,对用户模板进行同义词扩充,形成扩充后的用户模板,以此模板来进行文本过滤。在用户反馈的基础上,自适应地修改该模板,以适应用户变化的需求及改善系统过滤性能。实验表明,这样的确可以提高系统覆盖面,提高系统效率。In this paper we first give some information about the text filtering and VSM(Vector Support Machine),then we introduce a model that build a concept-expanded-based profile.We use this concept-expanded profile to sift the information which may be of the user's interest.In the model,the profile is represented as a vector in the vector space.We use the synsets in WordNet to expand the profile automatically.The enrichment of profile with semantically-related terms can enhance recall,as it permits matching relevant text that could not contain any of the old profile terms.A filtering system should be able to adapt to user's interest changes,so we automatically modify the user model to recognize the changes.Experimental results show that the methods can improve the text filtering performance.

关 键 词：概念扩充 向量空间 用户模板 文本表示 WORDNET 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]