English

Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog

Computation and Language 2021-04-13 v1 Machine Learning

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. Our code is available at https://github.com/facebookresearch/pytext

Keywords

Cite

@article{arxiv.2104.04923,
  title  = {Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog},
  author = {Arun Babu and Akshat Shrivastava and Armen Aghajanyan and Ahmed Aly and Angela Fan and Marjan Ghazvininejad},
  journal= {arXiv preprint arXiv:2104.04923},
  year   = {2021}
}
R2 v1 2026-06-24T01:02:49.352Z