A hierarchical neural model for learning sequences of dialogue acts

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

    13 Citations (Scopus)


    We propose a novel hierarchical Recurrent Neural Network (RNN) for learning sequences of Dialogue Acts (DAs). The input in this task is a sequence of utterances (i.e., conversational contributions) comprising a sequence of tokens, and the output is a sequence of DA labels (one label per utterance). Our model leverages the hierarchical nature of dialogue data by using two nested RNNs that capture long-range dependencies at the dialogue level and the utterance level. This model is combined with an attention mechanism that focuses on salient tokens in utterances. Our experimental results show that our model outperforms strong baselines on two popular datasets, Switchboard and MapTask; and our detailed empirical analysis highlights the impact of each aspect of our model.

    Original languageEnglish
    Title of host publication15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017)
    Subtitle of host publicationProceedings of Conference, Volume 1: Long Papers, April 3-7, 2017, Valencia, Spain
    EditorsPhil Blunsom, Alexander Koller
    Place of PublicationStroudsburg, PA
    PublisherAssociation for Computational Linguistics (ACL)
    Number of pages10
    ISBN (Electronic)9781510838604
    ISBN (Print)9781945626340
    Publication statusPublished - 2017
    EventEuropean Association of Computational Linguistics Conference 2017 - Valencia, Spain
    Duration: 3 Apr 20177 Apr 2017
    Conference number: 15th


    ConferenceEuropean Association of Computational Linguistics Conference 2017
    Abbreviated titleEACL 2017

    Cite this