A novel method for measuring semantic similarity for XML schema matching

Enterprises integration has recently gained great attentions, as never before. The paper deals with an essential activity enabling seamless enterprises integration, that is, a similarity-based schema matching. To this end, we present a supervised approach to measure semantic similarity between XML schema documents, and, more importantly, address a novel approach to augment reliably labeled training data from a given few labeled samples in a semi-supervised manner. Experimental results reveal the proposed method is very cost-efficient and reliably predicts semantic similarity.