A generative attentional neural network model for dialogue act classification

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

    8 Citations (Scopus)

    Abstract

    We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.

    Original languageEnglish
    Title of host publicationAnnual Meeting of the Association for Computational Linguistics 2017
    Subtitle of host publicationShort Papers, ACL 2017 - Proceedings
    EditorsRegina Barzilay, Min-Yen Kan
    Place of PublicationPA USA
    PublisherAssociation for Computational Linguistics (ACL)
    Pages524-529
    Number of pages6
    Volume2
    ISBN (Electronic)9781945626760
    DOIs
    Publication statusPublished - 2017
    EventAnnual Meeting of the Association of Computational Linguistics 2017 - Vancouver, Canada
    Duration: 30 Jul 20174 Aug 2017
    Conference number: 55th

    Conference

    ConferenceAnnual Meeting of the Association of Computational Linguistics 2017
    Abbreviated titleACL 2017
    CountryCanada
    CityVancouver
    Period30/07/174/08/17

    Cite this

    Tran, Q. H., Zukerman, I., & Haffari, G. (2017). A generative attentional neural network model for dialogue act classification. In R. Barzilay, & M-Y. Kan (Eds.), Annual Meeting of the Association for Computational Linguistics 2017: Short Papers, ACL 2017 - Proceedings (Vol. 2, pp. 524-529). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2083