Résumé
Most of the schema matching tools are assembled from multiple match algorithms, each employing a particular technique to improve matching accuracy and making matching systems extensible and customizable to a specific domain. Recently, it has been pointed out that the main issue is how to select the most suitable match algorithms to execute for a given domain and how to adjust the multiple parameters. The solutions provided by current schema matching tools consist in aggregating the results obtained by several match algorithms to improve the quality of the discovered matches. In this article, we present a novel method to replace this aggregation function and its drawbacks. Unlike other composite matchers, our matching engine makes use of a decision tree to combine the most appropriate match algorithms. As a first consequence, the performance of the system is improved since only a subset of match algorithms from a large library is used. The second advantage is the improvement of the quality of matches. Indeed, for a given domain, only the most suitable match algorithms are used. Our approach is also able to learn the most appropriate match algorithms for a given domain by relying on the expert feedback. It can also selftune some parameters like thresholds and the performance versus quality ratio.