Résumé
To improve the matching accuracy, most of the schema matching tools aggregate the results obtained by several matching algorithms. The quality of matches depends on the adequacy and of the number of match algorithms used, and their combination and aggregation strategy. However, this aggregation entails several drawbacks on the performance, quality and tuning aspects. In this paper, we present a novel method for combining schema matching algorithms, which enables to avoid these drawbacks. Unlike other composite matchers, it is able to learn the most appropriate match algorithms for a given schema matching scenario. Thus, the matching engine makes use of a decision tree to combine most appropriate match algorithms. As a first consequence of using the decision tree, the performance of the system is improved since the complexity is bounded by the height of the decision tree. For this purpose, for a given domain, only the most suitable match algorithms are used from a large library of match algorithms. The second advantage is the improvement of the quality of matches.