Vocabulary Alignment in Openly Specified Interactions

Abstract: The problem of achieving common understanding between agents that use different vocabularies has been mainly addressed by designing techniques that explicitly negotiate mappings between their vocabularies, requiring agents to share a meta-language. In this paper we consider the case of agents that use different vocabularies and have no meta-language in common, but share the knowledge of how to perform a task, given by the specification of an interaction protocol. For this situation, we present a framework that lets agents learn a vocabulary alignment from the experience of interacting. Unlike previous work in this direction, we use open protocols that constrain possible actions instead of defining procedures, making our approach more general. We present two techniques that can be used either to learn an alignment from scratch or to repair an existent one, and we evaluate experimentally their performance.