We present an architecture for spoken dialogue systems where first-order inference (both theorem proving and model building) plays a crucial role in interpreting utterances of dia...
We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment a...
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
Satinder P. Singh, Diane J. Litman, Michael J. Kea...
Language users have individual linguistic styles. A spoken dialogue system may benefit from adapting to the linguistic style of a user in input analysis and output generation. To ...
This paper describes a novel method by which a spoken dialogue system can learn to choose an optimal dialogue strategy from its experience interacting with human users. The method...