PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Yunshui Li, Binyuan Hui, ZhiChao Yin, Min Yang, Fei Huang, Yongbin Li
Abstract
Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited availability of multi-modal dialogue data, there is still scarce research on multi-modal dialogue pre-training. Yet another intriguing challenge emerges from the encompassing nature of multi-modal dialogue, which involves various modalities and tasks. Moreover, new forms of tasks may arise at unpredictable points in the future. Hence, it is essential for designed multi-modal dialogue models to possess sufficient flexibility to adapt to such scenarios. This paper proposes PaCE, a unified, structured, compositional multi-modal dialogue pre-training framework. It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data. Furthermore, we propose a progressive training method where old experts from the past can assist new experts, facilitating the expansion of their capabilities. Experimental results demonstrate that PaCE achieves state-of-the-art results on eight multi-modal dialog benchmarks.- Anthology ID:
- 2023.acl-long.749
- 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:
- 13402–13416
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.749
- DOI:
- 10.18653/v1/2023.acl-long.749
- Cite (ACL):
- Yunshui Li, Binyuan Hui, ZhiChao Yin, Min Yang, Fei Huang, and Yongbin Li. 2023. PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13402–13416, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts (Li et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.acl-long.749.pdf