摘要
To further enhance the efficiencies of search engines,achieving capabilities of searching,indexing and locating the information in the deep web,latent semantic analysis is a simple and effective way.Through the latent semantic analysis of the attributes in the query interfaces and the unique entrances of the deep web sites,the hidden semantic structure information can be retrieved and dimension reduction can be achieved to a certain extent.Using this semantic structure information,the contents in the site can be inferred and the similarity measures among sites in deep web can be revised.Experimental results show that latent semantic analysis revises and improves the semantic understanding of the query form in the deep web,which overcomes the shortcomings of the keyword-based methods.This approach can be used to effectively search the most similar site for any given site and to obtain a site list which conforms to the restrictions one specifies.
为了进一步提高搜索引擎的效率,实现对deep web中所蕴含的大量有用信息的检索、索引和定位,引入潜在语义分析理论是一种简单而有效的方法.通过对作为deep web站点入口的查询界面里的表单属性进行潜在语义分析,从表单属性中挖掘出潜在语义结构,并实现一定程度上的降维.利用这种潜在语义结构,推断对应站点的数据内容并改善不同站点的相似度计算.实验结果显示,潜在语义分析修正和改善了deep web站点的表单属性的语义理解,弥补了单纯的关键字匹配带来的一些不足.该方法可以被用来实现为某一站点查找网络上相似度高的站点及通过键入表单属性给出拥有相似表单的站点列表.
