Abstract
Traditional end-to-end task-oriented dialog systems first convert dialog context into belief state and action state before generating the system response. The system response performance is significantly affected by the quality of the belief state and action state. We first explore what dialog context representation is beneficial to improving the quality of the belief state and action state, which further enhances the generated response quality. To tackle our exploration, we propose Mars, an end-to-end task-oriented dialog system with two contrastive learning strategies to model the relationship between dialog context and belief/action state representations. Empirical results show dialog context representations, which are more different from semantic state representations, are more conducive to multi-turn task-oriented dialog. Moreover, our proposed Mars achieves state-of-the-art performance on the MultiWOZ 2.0, CamRest676, and CrossWOZ.- Anthology ID:
- 2023.findings-acl.708
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11139–11160
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.708
- DOI:
- 10.18653/v1/2023.findings-acl.708
- Cite (ACL):
- Haipeng Sun, Junwei Bao, Youzheng Wu, and Xiaodong He. 2023. Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11139–11160, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog (Sun et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.findings-acl.708.pdf