Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu
Abstract
Existing controllable dialogue generation work focuses on the single-attribute control and lacks generalization capability to out-of-distribution multiple attribute combinations. In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations. We propose a prompt-based disentangled controllable dialogue generation model, DCG. It learns attribute concept composition by generating attribute-oriented prompt vectors and uses a disentanglement loss to disentangle different attributes for better generalization. Besides, we design a unified reference-free evaluation framework for multiple attributes with different levels of granularities. Experiment results on two benchmarks prove the effectiveness of our method and the evaluation metric.- Anthology ID:
- 2023.acl-long.793
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14179–14196
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.793
- DOI:
- 10.18653/v1/2023.acl-long.793
- Cite (ACL):
- Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, and Weiran Xu. 2023. Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14179–14196, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (Zeng et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.793.pdf