Recognizing and Extracting Relations in Web Tables and Lists
识别和抽取Web列表中的关系信息

There is a lot of relation information in all kinds of tables and lists on the Web. But using search engines it is not easy to find them. In this paper, a method based on semantics and datum feature is proposed. It can be used to recognize and extract the desired relation information from tables and lists on the Web. We set up a model to describe the desired relation first, and then search the Web to find table and lists. For each found table or list, evaluate if it contains desired relation. If evaluation is big enough, our system will extract relation information from the table or list.