English

There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning

Computation and Language 2022-10-25 v1

Abstract

Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, the existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multi-reference KGC dataset and propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the one-to-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.

Keywords

Cite

@article{arxiv.2210.12459,
  title  = {There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning},
  author = {Xueliang Zhao and Tingchen Fu and Chongyang Tao and Rui Yan},
  journal= {arXiv preprint arXiv:2210.12459},
  year   = {2022}
}

Comments

To appear at EMNLP 2022 main conference. The first two authors contributed equally

R2 v1 2026-06-28T04:15:14.538Z