End-to-end evaluations of conversational dialogue systems with naive users are currently uncovering severe usability problems that result in low task completion rates. Preliminary...
Given the growing complexity of tasks that spoken dialogue systems are trying to handle, Reinforcement Learning (RL) has been increasingly used as a way of automatically learning ...
This paper describes a method for the development of dialogue managers for natural language interfaces. A dialogue manager is presented designed on the basis of both a theoretical...
This paper introduces a new dialogue management framework for goal-directed conversations. A declarative specification defines the domain-specific elements and guides the dialogue...
Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speec...