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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.793.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.793.mp4