Regularizing Dialogue Generation by Imitating Implicit Scenarios
Shaoxiong Feng, Xuancheng Ren, Hongshen Chen, Bin Sun, Kan Li, Xu Sun
Abstract
Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge. More importantly, the conversation scenarios are further internalized using imitation learning framework, where the conventional dialogue model that has no access to future conversations is effectively regularized by transferring the scenario knowledge contained in hierarchical supervising signals from the scenario-based dialogue model, so that the future conversation is not required in actual inference. Extensive evaluations show that our approach significantly outperforms state-of-the-art baselines on diversity and relevance, and expresses scenario-specific knowledge.- Anthology ID:
- 2020.emnlp-main.534
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6592–6604
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.534
- DOI:
- 10.18653/v1/2020.emnlp-main.534
- Cite (ACL):
- Shaoxiong Feng, Xuancheng Ren, Hongshen Chen, Bin Sun, Kan Li, and Xu Sun. 2020. Regularizing Dialogue Generation by Imitating Implicit Scenarios. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6592–6604, Online. Association for Computational Linguistics.
- Cite (Informal):
- Regularizing Dialogue Generation by Imitating Implicit Scenarios (Feng et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2020.emnlp-main.534.pdf
- Data
- DailyDialog, MultiWOZ, OpenSubtitles