NAACL 2021long26 citations

Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog

Arun Babu, Akshat Shrivastava, Armen Aghajanyan, Ahmed Aly, Angela Fan, Marjan Ghazvininejad

Abstract

Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-time conversational use cases has been stymied by higher compute requirements and thus higher latency. In this work, we propose a non-autoregressive approach to predict semantic parse trees with an efficient seq2seq model architecture. By combining non-autoregressive prediction with convolutional neural networks, we achieve significant latency gains and parameter size reduction compared to traditional RNN models. Our novel architecture achieves up to an 81% reduction in latency on TOP dataset and retains competitive performance to non-pretrained models on three different semantic parsing datasets.

BibTeX
@inproceedings{babu-etal-2021-non,
    title = "Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog",
    author = "Babu, Arun  and
      Shrivastava, Akshat  and
      Aghajanyan, Armen  and
      Aly, Ahmed  and
      Fan, Angela  and
      Ghazvininejad, Marjan",
    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.236/",
    doi = "10.18653/v1/2021.naacl-main.236",
    pages = "2969--2978"
}
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog · NAACL 2021