Discovering structural association of semistructured data

Abstract

Many semistructured objects are similarly, though not identically, structured. We study the problem of discovering 'typical' substructures of a collection of semistructured objects. The discovered structures can serve the following purposes: 1) the 'table-of-contents' for gaining general information of a source, 2) a road map for browsing and querying information sources, 3) a basis for clustering documents, 4) partial schemas for providing standard database access methods, and 5) user/customer's interests and browsing patterns. The discovery task is impacted by structural features of semistructured data in a nontrivial way and traditional data mining frameworks are inapplicable. We define this discovery problem and propose a solution.