摘要
从多记录网页中准确的自动抽取出需要的信息,是Web信息处理中的一个重要研究课题。针对现有方法对噪声敏感的缺点,该文提出了基于记录子树的最大相似度发现记录模式的思想,以在同类记录的表现模式存在一定差异的情况下正确识别记录。在此基础上,实现了多记录网页自动抽取系统,该系统可以从多个学术论文检索网站中,自动获取结果网页,并自动抽取其中的记录。对常见论文检索网站的实验表明了该系统具有较好的有效性和准确性。
Extracting information effectively and accurately from semi - structured web pages is an important research problem in Web Information processing. Traditional algorithms are sensitive to noise. This paper puts forward a method for discovering the record model based on Maximal Similar Sub Tree, to identify records automatically and correctly when there are some differences in expression models of records that belong to the same type. Furthermore, a multi - record web page extraction system was is to extract information from result pages of paper searching websites automatically. The experiments made through with some common paper searching websites have demonstrated that this system has high efficiency and accuracy.
出处
《计算机仿真》
CSCD
2005年第12期95-97,142,共4页
Computer Simulation
基金
863重大专项3TNET"宽带信息网流媒体业务分发集成平台的研制"(2003AA103810)
关键词
互联网挖掘
信息集成
自动信息抽取
Web mining
Information integration
Automatic information extraction
