Extracting Result Schema Based on Query Instances in the Deep Web

摘要

Deep Web sources contain a large of high-quality andquery-related structured date. One of the challenges in the DeepWeb is extracting result schemas of Deep Web sources. To address this challenge, this paper describes a novel approach thatextracts both result data and the result schema of a Web database.The approach first models the query interface of a Deep Websource and fills in it with a specifically query instance. Then theresult pages of the Deep Web sources are formatted in the treestructure to retrieve subtrees that contain elements of the queryinstance. Next, result schema of the Deep Web source is extractedby matching the subtree' nodes with the query instance, in which,a two-phase schema extraction method is adopted for obtainingmore accurate result schema. Finally, experiments on real DeepWeb sources show the utility of our approach, which provides ahigh precision and recall.