A plan-based agent architecture for interpreting natural language dialogue

This paper describes a plan-based agent architecture for modelling NL coope rative dialogue; in particular, the paper focuses on the Interpretation of dialogue and on the explanation of its coherence by means of the recognitio n of the speakers' underlying intentions. The approach we propose makes it possible to analyze an explain in a uniform way several apparently unrelate d linguistic phenomena, which have been often studied separately and treate d via ad-hoc methods in the models of dialogue presented in the literature. Our model of linguistic interaction is based on the idea that dialogue can be seen as any other interaction among agents: therefore, domain-level and linguistic actions are treated in a similar way. Our agent architecture is based on a two-level representation of the knowle dge about acting: at the metalevel, the agent modelling (AM) plans describe the recipes for plan formation and execution (they are a declarative repre sentation of a reactive planner); at the object level, the domain and commu nicative actions are defined. The AM plans are used to identify the goals u nderlying the actions performed by an observed agent; the recognized plans constitute the dialogue context, where the intentions of all participants a re stored in a structured way, in order to be used in the interpretation of the subsequent dialogue turns. (C) 2000 Academic Press.