An Algorithm for Plan Recognition in Collaborative Discourse

A model of plan recognition in discourse must be based on intended recognition, distinguish each agent's beliefs and intentions from the other's, and avoid assumptions about the correctness or completeness of the agents' beliefs. In this paper, we present an algorithm for plan recognition that is based on the Shared-Plan model of collaboration (Grosz and Sidner, 1990; Lochbaum et al., 1990) and that satisses these constraints. Introduction To make sense of each other's utterances, conversational participants must recognize the intentions behind those utterances. Thus, a model of intended plan recognition is an important component of a theory of discourse understanding. The model must distinguish each agent's beliefs and intentions from the other's and avoid assumptions about the correctness or completeness of the agents' beliefs. has argued, because these systems do not diierentiate between the beliefs and intentions of the diierent conversational participants, they are insuucient for modelling discourse. Although Pollack proposes a model that does make this distinction , her model has other shortcomings. In particular, it assumes a master/slave relationship between agents (Grosz and Sidner, 1990) and that the inferring agent has complete and accurate knowledge of domain actions. In addition, like many earlier systems, it relies upon a set of heuristics to control the application of plan inference rules. In contrast, Kautz (1987; 1990) presented a theoretical formalization of the plan recognition problem,