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.
The development of spoken dialogue systems for rich, open-ended interactions raises a number of challenges, one of which is dialogue management.
2.1 Partially Observable Markov Decision Processes (POMDPs)
3.1 Control knowledge
4.1 General comments
This paper described a new approach to exploit relational models of dialogue structure for controlling the action space in POMDPs.