Toward Affective Dialogue Modeling using Partially Observable Markov Decision Processes

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    68 Downloads (Pure)

    Abstract

    We propose a novel approach to developing a dialogue model which is able to take into account some aspects of the user’s emotional state and acts appropriately. The dialogue model uses a Partially Observable Markov Decision Process approach with observations composed of the observed user’s emotional state and action. A simple example of route navigation is explained to clarify our approach and preliminary results & future plans are briefly discussed.
    Original languageEnglish
    Title of host publicationProceedings of the 1st workshop on Emotion and Computing - Current Research and Future Impact
    EditorsD. Reichardt, P. Levi, J.J.C. Meyer
    Place of PublicationBremen
    PublisherUniversity of Bremen
    Pages47-50
    Number of pages4
    Volume2
    ISBN (Print)3-88722-664-X
    Publication statusPublished - Jun 2006
    Event1st workshop on Emotion and Computing – Current Research and Future Impact - Bremen, Germany
    Duration: 19 Jun 200619 Jun 2006

    Workshop

    Workshop1st workshop on Emotion and Computing – Current Research and Future Impact
    Period19/06/0619/06/06
    Other19 Jun 2006

    Keywords

    • HMI-MI: MULTIMODAL INTERACTIONS
    • HMI-SLT: Speech and Language Technology
    • Partially observable Markov decision process (POMDP)
    • Markov decision process (MDP)

    Fingerprint Dive into the research topics of 'Toward Affective Dialogue Modeling using Partially Observable Markov Decision Processes'. Together they form a unique fingerprint.

    Cite this