Exploring Features and Classifiers for Dialogue Act Segmentation

Harm op den Akker, Hendrikus J.A. op den Akker, Christian Schulz

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

    5 Citations (Scopus)
    52 Downloads (Pure)

    Abstract

    This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.
    Original languageUndefined
    Title of host publicationMachine Learning for Multimodal Interaction, MLMI 2008
    EditorsAndrei Popescu-Belis, Rainer Stiefelhagen
    Place of PublicationBerlin / Heidelberg
    PublisherSpringer
    Pages196-207
    Number of pages12
    ISBN (Print)978-3-540-85852-2
    DOIs
    Publication statusPublished - 20 Sept 2008
    Event5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008: 5th Joint Workshop on Machine Learning and Multimodal Interaction - Utrecht, the Netherlands, Berlin
    Duration: 8 Sept 200810 Sept 2008

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Volume5237

    Conference

    Conference5th International Workshop on Machine Learning and Multimodal Interaction, MLMI 2008
    CityBerlin
    Period8/09/0810/09/08
    Other8-10 September 2008

    Keywords

    • HMI-MI: MULTIMODAL INTERACTIONS
    • EC Grant Agreement nr.: FP6/0033812
    • EWI-14954
    • IR-65340
    • Machine classification
    • METIS-255875
    • Conversational Analysis

    Cite this