Learn More
Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular , the degree to(More)
The lack of suitable training and testing data is currently a major roadblock in applying machine-learning techniques to dialogue management. Stochastic modelling of real users has been suggested as a solution to this problem, but to date few of the proposed models have been quantitatively evaluated on real data. Indeed , there are no established criteria(More)
This paper describes a method for automatic design of human-computer dialogue strategies by means of reinforcement learning, using a dialogue simulation tool to model the user behaviour and system recognition performance. To the authors' knowledge this is the first application of a detailed simulation tool to this problem. The simulation tool is trained on(More)
Partially Observable Markov Decision Processes (POMDPs) have been shown to be a promising framework for dialog management in spoken dialog systems. However, to date, POMDPs have been limited to artificially small tasks. In this work, we present a novel method called a " Summary POMDP " for scaling slot-filling POMDP-based dialog managers to cope with tasks(More)
Within all CUED spoken dialogue systems, interactions at the intention level are represented by a core set of dialogue acts. A key feature of the CUED scheme is the provision for representing a distribution of dialogue act hypotheses. To obviate the need for combining multiple acts and the consequent normalisation issues that this would raise, CUED dialogue(More)