跳到主要导航 跳到搜索 跳到主要内容

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

  • Xueliang Zhao
  • , Tingchen Fu
  • , Chongyang Tao
  • , Rui Yan*
  • *此作品的通讯作者
  • Peking University
  • Gaoling School of Artificial Intelligence
  • Microsoft USA

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
编辑Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
出版商Association for Computational Linguistics (ACL)
1878-1891
页数14
ISBN(电子版)9781959429401
DOI
出版状态已出版 - 2022
已对外发布
活动2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Hybrid, Abu Dhabi, 阿拉伯联合酋长国
期限: 7 12月 202211 12月 2022

出版系列

姓名Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

会议

会议2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
国家/地区阿拉伯联合酋长国
Hybrid, Abu Dhabi
时期7/12/2211/12/22

指纹

探究 'There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此