Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Multiple Constraint Acquisition / 698
Robin Arcangioli, Christian Bessiere, Nadjib Lazaar

QUACQ is a constraint acquisition system that assists a non-expert user to model her problem as a constraint network by classifying (partial) examples as positive or negative. For each negative example, QUACQ focuses onto a constraint of the target network. The drawback is that the user may need to answer a great number of such examples to learn all the constraints. In this paper, we provide a new approach that is able to learn a maximum number of constraints violated by a given negative example. Finally we give an experimental evaluation that shows that our approach improves on QUACQ.