Learning the Reward Model of Dialogue POMDPs from Data

  title={Learning the Reward Model of Dialogue POMDPs from Data},
  author={Abdeslam Boularias and Hamid R. Chinaei and Brahim Chaib-draa},
Spoken language communication between human and machines has become a challenge in research and technology. In particular, enabling the health care robots with spoken language interface is of great attention. Recently due to uncertainty characterizing dialogues, there has been interest for modelling the dialogue manager of spoken dialogue systems using Partially Observable Markov Decision Processes (POMDPs). In this context, we would like to learn the reward model of dialogue POMDPs from expert… CONTINUE READING


Publications referenced by this paper.

Notes regarding computations in openhtmm

  • Amit Gruber, Ashok Popat
  • 2007
1 Excerpt

A framework for wizard-of-oz experiments with a simulated asr-channel

  • Steve Young
  • In Proc Intl Conf on Speech and Language…
  • 2004
2 Excerpts

The SACTI-2 Corpus: Guide for Research Users, Cambridge University

  • Karl Weilhammer, Jason D. Williams, Steve Young
  • Technical report,
  • 2004
2 Excerpts

Similar Papers

Loading similar papers…