Tree Mining Application to Matching of Heterogeneous Knowledge Representations

Matching of heterogeneous knowledge sources is of increasing importance in areas such as scientific knowledge management, e-commerce, enterprise application integration, and many emerging Semantic Web applications. With the desire of knowledge sharing and reuse in these fields, it is common that the knowledge coming from different organizations from the same domain is to be matched. We propose a knowledge matching method based on our previously developed tree mining algorithms for extracting frequently occurring subtrees from a tree structured database such as XML. Using the method the common structure among the different representations can be automatically extracted. Our focus is on knowledge matching at the structural level and we use a set of example XML schema documents from the same domain to evaluate the method. We discuss some important issues that arise when applying tree mining algorithms for detection of common document structures. The experiments demonstrate the usefulness of the approach.