Dialogue-act tagging using smart feature selection: results on multiple corpora

Daan Verbree, R.J. Rienks, Dirk K.J. Heylen

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

    35 Citations (Scopus)
    522 Downloads (Pure)

    Abstract

    This paper presents an overview of our on-going work on dialogueact classification. Results are presented on the ICSI, Switchboard, and on a selection of the AMI corpus, setting a baseline for forthcoming research. For these corpora the best accuracy scores obtained are 89.27%, 65.68% and 59.76%, respectively. We introduce a smart compression technique for feature selection and compare the performance from a subset of the AMI transcriptions with AMI-ASR output for the same subset.
    Original languageUndefined
    Title of host publicationFirst International IEEE Workshop on Spoken Language Technology SLT 2006
    EditorsB. Raorke
    Place of PublicationPalm Beach
    PublisherIEEE
    Pages70-73
    Number of pages4
    ISBN (Print)1-4244-0873-3
    DOIs
    Publication statusPublished - Dec 2006
    EventFirst International IEEE Workshop on Spoken Language Technology, SLT 2006 - Palm Beach, Aruba
    Duration: 10 Dec 200613 Dec 2006

    Publication series

    Name
    PublisherIEEE Computer Society
    Number10

    Workshop

    WorkshopFirst International IEEE Workshop on Spoken Language Technology, SLT 2006
    Period10/12/0613/12/06
    Other10-13 December 2006

    Keywords

    • EC Grant Agreement nr.: FP6/506811
    • EWI-9501
    • IR-67003
    • METIS-237662
    • HMI-CI: Computational Intelligence

    Cite this