A POMDP approach to Affective Dialogue Modeling

Trung H. Bui, Mannes Poel, Anton Nijholt, Job Zwiers

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

    65 Downloads (Pure)

    Abstract

    We propose a novel approach to developing a dialogue model that is able to take into account some aspects of the user's affective state and to act appropriately. Our dialogue model uses a Partially Observable Markov Decision Process approach with observations composed of the observed user's affective state and action. A simple example of route navigation is explained to clarify our approach. The preliminary results showed that: (1) the expected return of the optimal dialogue strategy depends on the correlation between the user's affective state & the user's action and (2) the POMDP dialogue strategy outperforms five other dialogue strategies (the random, three handcrafted and greedy action selection strategies).
    Original languageEnglish
    Title of host publicationProceedings workshop on The Fundamentals of Verbal and Non-verbal Communication and the Biometrical Issue
    EditorsE. Keller, M. Marinaro, M. Bratanic
    Place of PublicationAmsterdam
    PublisherIOS
    Pages349-355
    Number of pages7
    Volume1
    ISBN (Print)978-158603-733-8
    Publication statusPublished - 1 Jan 2007
    EventNATO-ASI Summer School on Fundamentals of Verbal and Nonverbal Communication and the Biometrical Issue 2006 - Vietri sul Mare, Italy
    Duration: 2 Sept 200612 Sept 2006

    Publication series

    NameNATO Security through Science Series - E: Human and Societal Dynamics
    PublisherIOS Press
    Volume18

    Workshop

    WorkshopNATO-ASI Summer School on Fundamentals of Verbal and Nonverbal Communication and the Biometrical Issue 2006
    Country/TerritoryItaly
    CityVietri sul Mare
    Period2/09/0612/09/06

    Keywords

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

    Fingerprint

    Dive into the research topics of 'A POMDP approach to Affective Dialogue Modeling'. Together they form a unique fingerprint.

    Cite this