自动分类研究现状与展望  

Research on the Automatic Classification:Present Situation and Prospects

作　　者：成颖[1] 史九林[1] 

机构地区：[1]南京大学信息管理系

出　　处：《情报学报》1999年第1期20-26,共7页Journal of the China Society for Scientific and Technical Information

摘　　要：自动分类包括自动聚类、自动归类及类号间的自动转换三个方面。自动聚类由于其复杂性，实际使用尚少。本文在回顾我国自动分类的历史和现状的基础上，分析了我国自动分类研究存在的不足，指出基于自然语言理解的分类专家系统是自动分类研究的发展方向。Automatic classification comprises three sections,i.e. automatic clustering,automatic grouping and automatic convertion of class number.In this paper,the author reviews methods of the automatic clustering and points out why it has seldom been applied in practice.The history and present situation of automatic grouping in our country have also been reviewed,and the author has an analysis of the weakness in the field and holds that the research on the automatic classification is oriented to the expert system of automatic classification with the application of NLP.

关 键 词：自动分类 专家系统 自然语言理解 

分 类 号：G254.1[文化科学—图书馆学] G254－39