Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

Dingmin Wang; Chenghua Lin; Qi Liu; Kam-Fai Wong

NAACL 2021long18 citations

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

Dingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong

Abstract

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for clas- sification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.

BibTeX

@inproceedings{wang-etal-2021-fast,
    title = "Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition",
    author = "Wang, Dingmin  and
      Lin, Chenghua  and
      Liu, Qi  and
      Wong, Kam-Fai",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.27/",
    doi = "10.18653/v1/2021.naacl-main.27",
    pages = "289--295"
}