一种基于Domain Ontology的Web文档抽取机制  

A Mechanismof Web Document Extraction Based on Domain Ontology

作　　者：周运[1] 牟占生[1] 

机构地区：[1]河南师范大学计算机与信息技术学院,河南新乡453007

出　　处：《河南师范大学学报（自然科学版）》2009年第3期124-126,共3页Journal of Henan Normal University(Natural Science Edition)

基　　金：河南省教育厅自然科学基础研究计划资助项目(2007520022);河南省自然科学基金(092300410152)

摘　　要：以小学生数学学习障碍的问题领域为研究对象,通过领域本体的应用,从搜索到的文档中抽取重要句子形成摘要.利用领域本体能够描述特定知识领域内相关的概念和关系这种特性,提出了一个改进的以多个关键词来评判文档段落重要性的方法,用此方法的查询结果更符合学习者需要.Focusing on the math learning disabilities of pupils in primary school, the abstract can be formed by extracting the major sentences from the retrieved documents based on the.application of Domain Ontology. Applying Domain Ontology, the related concept and relationship in the particular knowledge domain can be described. In this paper, an improved approach which identifies the paragraph significance based on multiple key words is proposed. The inquired results obtained by this approach better meet the learner＇s needs.

关 键 词：文本挖掘 文本摘要 知识抽取 本体 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]