Representing Communicative Intentions in Collaborative Conversational Agents

This paper pursues a formal analogy between natural language dialogue and collaborative real-world action in general. The analogy dependson an analysis of two aspects of collaboration that figure crucially in language use. First, agents must be able to coordinate abstractly about future decisions which cannot be made on present information. Second, when agents finally take such decisions, they must again coordinate in order to interpret one anothers’ actions as collaborative. The contribution of this paper is a general representation of collaborative plans and intentions, inspired by representations of deductions in logics of knowledge, action and time, which supports these two kinds of coordination. Such representations can describe natural language dialogue simply by specifying the potential that utterances have, in virtue of their meanings, to contribute to an evolving record of the conversation. These representations are implemented in a simple prototype collaborative dialogue agent.