A Method of Schema Matching Based on Top-K Mapping and User Feedback

The matching has been recognized as a plausible solution for the semantic heterogeneity problem in many traditional applications, such as schema integration, ontology integration, data warehouses, data integration, and so on. In this paper, we introduce a new method of Schema Matching based on top-k schema mapping and user feedback. The essence of this method is the simultaneous generation of K best schema mappings and combination with user feedback to identify useful mappings. First it calculates the similarity values between two schema attributes, and then uses these attributes similarity values to generate K best schema mappings. After that, in an iterative process, the method could select an attribute whose entropy is the largest to return to user for making deciding. The user feedback could be used in the next iteration. Experiments show that our method could achieve a higher precision and recall.