tailieunhanh - Báo cáo khoa học: "Towards Relational POMDPs for Adaptive Dialogue Management"

Open-ended spoken interactions are typically characterised by both structural complexity and high levels of uncertainty, making dialogue management in such settings a particularly challenging problem. Traditional approaches have focused on providing theoretical accounts for either the uncertainty or the complexity of spoken dialogue, but rarely considered the two issues simultaneously. | Towards Relational POMDPs for Adaptive Dialogue Management Pierre Lison Language Technology Lab German Research Centre for Artificial Intelligence DFKI GmbH Saarbrucken Germany Abstract Open-ended spoken interactions are typically characterised by both structural complexity and high levels of uncertainty making dialogue management in such settings a particularly challenging problem. Traditional approaches have focused on providing theoretical accounts for either the uncertainty or the complexity of spoken dialogue but rarely considered the two issues simultaneously. This paper describes ongoing work on a new approach to dialogue management which attempts to fill this gap. We represent the interaction as a Partially Observable Markov Decision Process POMDP over a rich state space incorporating both dialogue user and environment models. The tractability of the resulting POMDP can be preserved using a mechanism for dynamically constraining the action space based on prior knowledge over locally relevant dialogue structures. These constraints are encoded in a small set of general rules expressed as a Markov Logic network. The first-order expressivity of Markov Logic enables us to leverage the rich relational structure of the problem and efficiently abstract over large regions of the state and action spaces. 1 Introduction The development of spoken dialogue systems for rich open-ended interactions raises a number of challenges one of which is dialogue management. The role of dialogue management is to determine which communicative actions to take . what to say given a goal and particular observations about the interaction and the current situation. Dialogue managers have to face several issues. First spoken dialogue systems must usually deal with high levels of noise and uncertainty. These uncertainties may arise from speech recognition errors limited grammar coverage or from various linguistic and pragmatic ambiguities. Second open-ended dialogue is characteristically