Iterative Perceptual Learning for Social Behavior Synthesis

I.A. de Kok, Ronald Walter Poppe, Dirk K.J. Heylen

    Research output: Book/ReportReportProfessional

    57 Downloads (Pure)

    Abstract

    We introduce Iterative Perceptual Learning (IPL), a novel approach for learning computational models for social behavior synthesis from corpora of human-human interactions. The IPL approach combines perceptual evaluation with iterative model refinement. Human observers rate the appropriateness of synthesized individual behaviors in the context of a conversation. These ratings are in turn used to refine the machine learning models. As the ratings correspond to those moments in the conversation where the production of a specific social behavior is inappropriate, we can regard features extracted at these moments as negative samples for the training of a machine learning classifier. This is an advantage over traditional corpusbased approaches, in which negative samples at extracted at random from moments in the conversation where the specific social behavior does not occur. We perform a comparison between the IPL approach and the traditional corpus-based approach on the timing of backchannels for a listener in speaker-listener dialogs. While both models perform similarly in terms of precision and recall scores, the results of the IPL model are rated as more appropriate in the perceptual evaluation.We additionally investigate the effect of the amount of available training data and the variation of training data on the outcome of the models.
    Original languageUndefined
    Place of PublicationEnschede
    PublisherCentre for Telematics and Information Technology (CTIT)
    Number of pages9
    Publication statusPublished - Feb 2012

    Publication series

    NameCTIT Technical Report Series
    PublisherUniversity of Twente, Centre for Telematics and Information Technology (CTIT)
    No.TR-CTIT-12-01
    ISSN (Print)1381-3625

    Keywords

    • METIS-285036
    • IR-79712
    • Backchannel
    • Machine Learning
    • Social behavior synthesis
    • EWI-21340
    • HMI-MI: MULTIMODAL INTERACTIONS
    • HMI-CI: Computational Intelligence
    • Perceptual evaluation

    Cite this

    de Kok, I. A., Poppe, R. W., & Heylen, D. K. J. (2012). Iterative Perceptual Learning for Social Behavior Synthesis. (CTIT Technical Report Series; No. TR-CTIT-12-01). Enschede: Centre for Telematics and Information Technology (CTIT).
    de Kok, I.A. ; Poppe, Ronald Walter ; Heylen, Dirk K.J. / Iterative Perceptual Learning for Social Behavior Synthesis. Enschede : Centre for Telematics and Information Technology (CTIT), 2012. 9 p. (CTIT Technical Report Series; TR-CTIT-12-01).
    @book{3140b6b5844047ecb08828137104d6cb,
    title = "Iterative Perceptual Learning for Social Behavior Synthesis",
    abstract = "We introduce Iterative Perceptual Learning (IPL), a novel approach for learning computational models for social behavior synthesis from corpora of human-human interactions. The IPL approach combines perceptual evaluation with iterative model refinement. Human observers rate the appropriateness of synthesized individual behaviors in the context of a conversation. These ratings are in turn used to refine the machine learning models. As the ratings correspond to those moments in the conversation where the production of a specific social behavior is inappropriate, we can regard features extracted at these moments as negative samples for the training of a machine learning classifier. This is an advantage over traditional corpusbased approaches, in which negative samples at extracted at random from moments in the conversation where the specific social behavior does not occur. We perform a comparison between the IPL approach and the traditional corpus-based approach on the timing of backchannels for a listener in speaker-listener dialogs. While both models perform similarly in terms of precision and recall scores, the results of the IPL model are rated as more appropriate in the perceptual evaluation.We additionally investigate the effect of the amount of available training data and the variation of training data on the outcome of the models.",
    keywords = "METIS-285036, IR-79712, Backchannel, Machine Learning, Social behavior synthesis, EWI-21340, HMI-MI: MULTIMODAL INTERACTIONS, HMI-CI: Computational Intelligence, Perceptual evaluation",
    author = "{de Kok}, I.A. and Poppe, {Ronald Walter} and Heylen, {Dirk K.J.}",
    year = "2012",
    month = "2",
    language = "Undefined",
    series = "CTIT Technical Report Series",
    publisher = "Centre for Telematics and Information Technology (CTIT)",
    number = "TR-CTIT-12-01",
    address = "Netherlands",

    }

    de Kok, IA, Poppe, RW & Heylen, DKJ 2012, Iterative Perceptual Learning for Social Behavior Synthesis. CTIT Technical Report Series, no. TR-CTIT-12-01, Centre for Telematics and Information Technology (CTIT), Enschede.

    Iterative Perceptual Learning for Social Behavior Synthesis. / de Kok, I.A.; Poppe, Ronald Walter; Heylen, Dirk K.J.

    Enschede : Centre for Telematics and Information Technology (CTIT), 2012. 9 p. (CTIT Technical Report Series; No. TR-CTIT-12-01).

    Research output: Book/ReportReportProfessional

    TY - BOOK

    T1 - Iterative Perceptual Learning for Social Behavior Synthesis

    AU - de Kok, I.A.

    AU - Poppe, Ronald Walter

    AU - Heylen, Dirk K.J.

    PY - 2012/2

    Y1 - 2012/2

    N2 - We introduce Iterative Perceptual Learning (IPL), a novel approach for learning computational models for social behavior synthesis from corpora of human-human interactions. The IPL approach combines perceptual evaluation with iterative model refinement. Human observers rate the appropriateness of synthesized individual behaviors in the context of a conversation. These ratings are in turn used to refine the machine learning models. As the ratings correspond to those moments in the conversation where the production of a specific social behavior is inappropriate, we can regard features extracted at these moments as negative samples for the training of a machine learning classifier. This is an advantage over traditional corpusbased approaches, in which negative samples at extracted at random from moments in the conversation where the specific social behavior does not occur. We perform a comparison between the IPL approach and the traditional corpus-based approach on the timing of backchannels for a listener in speaker-listener dialogs. While both models perform similarly in terms of precision and recall scores, the results of the IPL model are rated as more appropriate in the perceptual evaluation.We additionally investigate the effect of the amount of available training data and the variation of training data on the outcome of the models.

    AB - We introduce Iterative Perceptual Learning (IPL), a novel approach for learning computational models for social behavior synthesis from corpora of human-human interactions. The IPL approach combines perceptual evaluation with iterative model refinement. Human observers rate the appropriateness of synthesized individual behaviors in the context of a conversation. These ratings are in turn used to refine the machine learning models. As the ratings correspond to those moments in the conversation where the production of a specific social behavior is inappropriate, we can regard features extracted at these moments as negative samples for the training of a machine learning classifier. This is an advantage over traditional corpusbased approaches, in which negative samples at extracted at random from moments in the conversation where the specific social behavior does not occur. We perform a comparison between the IPL approach and the traditional corpus-based approach on the timing of backchannels for a listener in speaker-listener dialogs. While both models perform similarly in terms of precision and recall scores, the results of the IPL model are rated as more appropriate in the perceptual evaluation.We additionally investigate the effect of the amount of available training data and the variation of training data on the outcome of the models.

    KW - METIS-285036

    KW - IR-79712

    KW - Backchannel

    KW - Machine Learning

    KW - Social behavior synthesis

    KW - EWI-21340

    KW - HMI-MI: MULTIMODAL INTERACTIONS

    KW - HMI-CI: Computational Intelligence

    KW - Perceptual evaluation

    M3 - Report

    T3 - CTIT Technical Report Series

    BT - Iterative Perceptual Learning for Social Behavior Synthesis

    PB - Centre for Telematics and Information Technology (CTIT)

    CY - Enschede

    ER -

    de Kok IA, Poppe RW, Heylen DKJ. Iterative Perceptual Learning for Social Behavior Synthesis. Enschede: Centre for Telematics and Information Technology (CTIT), 2012. 9 p. (CTIT Technical Report Series; TR-CTIT-12-01).