: A Marriage made inHeaven ?

In this paper, Finite-State-Automata (FSA) and theorem-proving approaches to spoken dialogue systems (SLDS) are contrasted to each other. FSA are too rigid to deal with unpredictable user reactions, such as corrections or counter-questions, whereas plan-based approaches are usually too complex to be effectively used, given the unreliability of word recognition and the elliptical and unconven-tional nature of spontaneous speech. As an alternative, a Dialogue Manager architecture is proposed which uses knowledge on both the possible sequences of dialogue acts and the dynamic representation of the task and requirements for its fullllment. The behaviour of the speciic user is taken into consideration, including their expectations about the system and the service ooered, as are instances of miscommu-nication and disagreement in the course of the dialogue, and the successful completion of sub-plans relevant to the task and the dialogue ow.