An approach to mixed initiative spoken information retrieval dialogue

We present an approach to mixed initiative dialogue in acoustic user interf aces to databases. First, we discuss how we distinguish between initiative and control in mixed initiative information retrieval dialogue and how the notions of taking, keeping, and relinquishing initiative and control are re flected in our approach. Based on this discussion, we develop a dialogue pl anning algorithm. This algorithm distinguished between resources and routin es and between the type and the content of an utterance; type and content a re calculated separately by routines that reason on the resources - a dialo gue model, a dialogue history, and an application description. Through this division we achieve a dialogue where the system adapts to the user's attem pts at changing the direction of a dialogue. Finally, we argue that automat ic segmentation of the dialogue and automatic tracking of initiative and co ntrol is inherent to our approach.