Recovering uncertain mappings through structural validation and aggregation with the MoTo system

We present an automated ontology matching methodology, supported by various machine learning techniques, as implemented in the system MoTo. The methodology is two-tiered. On the first stage it uses a meta-learner to elicit certain mappings from those predicted by single matchers induced by a specific base-learner. Then, uncertain mappings are recovered passing through a validation process, followed by the aggregation of the individual predictions through linguistic quantifiers. Experiments on benchmark ontologies demonstrate the effectiveness of the methodology.