作者: Yiyao Lu , Hai He , Hongkun Zhao , Weiyi Meng , Clement Yu
关键词:
摘要: An increasing number of databases have become web accessible through HTML form-based search interfaces. The data units returned from the underlying database are usually encoded into result pages dynamically for human browsing. For to be machine processable, which is essential many applications such as deep collection and Internet comparison shopping, they need extracted out assigned meaningful labels. In this paper, we present an automatic annotation approach that first aligns on a page different groups in same group semantic. Then, each annotate it aspects aggregate annotations predict final label it. wrapper site automatically constructed can used new database. Our experiments indicate proposed highly effective.