English

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Computation and Language 2021-09-10 v1

Abstract

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed.

Keywords

Cite

@article{arxiv.2109.04084,
  title  = {Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems},
  author = {Yicheng Zou and Zhihua Liu and Xingwu Hu and Qi Zhang},
  journal= {arXiv preprint arXiv:2109.04084},
  year   = {2021}
}

Comments

Accepted by EMNLP 2021, 12 pages

R2 v1 2026-06-24T05:48:54.507Z