| 基于领域本体的SOM文本逐层聚类方法 |
| |
| 引用本文： | 朱恒民,马静,黄卫东.基于领域本体的SOM文本逐层聚类方法[J].情报学报,2008,27(6). |
| |
| 作者姓名： | 朱恒民 马静 黄卫东 |
| |
| 作者单位： | 1. 南京邮电大学经济与管理学院,南京,210003
2. 南京航空航天大学经济与管理学院,南京,210016 |
| |
| 基金项目： | 江苏省高校自然科学基金，江苏省社会科学基金 |
| |
| 摘 要： | 为了有效处理文本中的复杂语义问题,提出了一种基于领域本体的SOM文本逐层聚类方法.该方法基于领域本体的概念及其逻辑语义关系,将文本向量的表示从词的层面上升到主题概念层面,大大消减了文本向量的维数,提高了聚类效率.基于领域本体的概念层次关系,采用SOM算法实现文本的逐层聚类,以分层方式组织文档,方便用户由粗到精、由总体到局部地查阅文本集.通过无人机领域的Web文本聚类实验,验证了该方法的有效性.
|
| 关 键 词： | 领域本体 文本聚类 逐层聚类 文本挖掘 |
Layer-by-Layer SOM Text Clustering Method Based on Domain Ontology |
| |
| Zhu Hengmin,Ma Jing,Huang Weidong.Layer-by-Layer SOM Text Clustering Method Based on Domain Ontology[J].Journal of the China Society for Scientific andTechnical Information,2008,27(6). |
| |
| Authors: | Zhu Hengmin Ma Jing Huang Weidong |
| |
| Institution: | Zhu Hengmin~1 Ma Jing~2 Huang Weidong~1 1.College of Economics&Management,Nanjing University of Posts&Telecommunications,Nanjing 210003 2.College of Economics&Management,Nanjing University of Aeronautics&Astronautics,Nanjing 210016 |
| |
| Abstract: | In order to effectively process complex semantic problems in text,a SOM text clustering method based on domain ontology is proposed.It represents text vector with topic concepts instead of words based on domain ontology.Thus the dimension of text vector is reduced greatly and efficiency of clustering is improved.Based on hierarchical relations of ontology concepts,texts are clustered layer-by-layer with SOM algorithm,It's convenient for user to survey texts from totally to partly and from grossly to finely.... |
| |
| Keywords: | SOM |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
