期刊论文

An Information Extraction Based on Semantic Matching for Web Pages

中文

计算机工程与应用

1002-8331

2006

42

23

141-143

10.3321/j.issn:1002-8331.2006.23.043

国家自然科学基金

本校为其他机构

为了较好地解决信息过量难以消化、汉语词的歧义划分、Web信息形式不一致并且难以辨识的问题,文章提出了一种基于语义匹配的Web信息提取方法.该方法融合了网页分类、汉语分词、语义信息匹配方法,并给出了一种义素相似度,进而提出了一种基于语义的信息匹配方法来识别和提取网页信息项.基于这种Web信息提取方法的网上药品信息监管系统Web-MIND能够提取出网上药品广告的信息项,并具有较高的准确率.

Some problems exist in all these Web information,for example：difficulty in processing excessive information,Chinese word segmentation for the ambiguous words,the information of variable formats,and the recognition of information.In order to solve those problems,an information extraction of web pages based on semantic matching is proposed in this paper.The extraction method integrates the classification method of Web pages,segmentation method of Chinese words and semantic-matching method of information.Moreover,the extraction method proposes a ...