中文试题模糊自动分类  

Fuzzy automatic classification for Chinese test question

作　　者：林慧君[1] 彭宏[2] 

机构地区：[1]湛江教育学院计算机科学系,广东湛江524037 [2]华南理工大学计算机科学与工程学院,广东广州510641

出　　处：《计算机工程与设计》2008年第13期3526-3528,3548,共4页Computer Engineering and Design

基　　金：广东省科技攻关基金项目(2005B10101033);湛江教育学院2003科研基金项目(20034)

摘　　要：试题库是在线测试的基础,中文试题的自动分类技术可以提高试题的检索速度和组卷的准确性。中文试题所包含的关键字较少,关键字出现的频度难以掌握,语法结构相似性较大并固定等,利用试题解析算法将试题分解成关键字库和冗字库,建立关键字矩阵,考虑试题的相似性,引入模糊聚类分析技术,对关键字库进行聚类,得到各个主题的类别,通过计算优化后的隶属度对试题进行分类。Test Bank is the basis of test online. The technology of automatic classification for the Chinese test question can raise the speed of searching question. It can also improve the accuration of forming test paper. The Chinese test question has few keywords. It has the resemble and fix structure of grammar. Using decomposing test problems algorithms can separate the test problem into keywords database and spare words database. Keywords matrix is built, Resemble of test problem is being considered. Analysis technology of fuzzy clustering is leaded in. The key words are clustered. The classifications of each subject are gotten by the test problems. The test problems can classified by computing subordinative degree after optimization.

关 键 词：中文试题 自动分类 关键字矩阵 模糊聚类 模糊等价矩阵 隶属度 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]