@inproceedings{vanzo-etal-2019-hierarchical,
    title = "Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational {AI}: {HERMIT} {NLU}",
    author = "Vanzo, Andrea  and
      Bastianelli, Emanuele  and
      Lemon, Oliver",
    editor = "Nakamura, Satoshi  and
      Gasic, Milica  and
      Zukerman, Ingrid  and
      Skantze, Gabriel  and
      Nakano, Mikio  and
      Papangelis, Alexandros  and
      Ultes, Stefan  and
      Yoshino, Koichiro",
    booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
    month = sep,
    year = "2019",
    address = "Stockholm, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-5931/",
    doi = "10.18653/v1/W19-5931",
    pages = "254--263",
    abstract = "We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45{\%} improvement in entity tagging F-score over Rasa, Dialogflow and LUIS."
}