Abstract
The end-to-end task-oriented dialogue system has achieved great success in recent years. Most of these dialogue systems need to accommodate multi-domain dialogue in real-world scenarios. However, due to the high cost of dialogue data annotation and the scarcity of labeled dialogue data, existing methods are difficult to extend to new domains. Therefore, it is important to use limited data to construct multi-domain dialogue systems. To solve this problem, we propose a novel domain attention module. It use the distributional signatures to construct a multi-domain dialogue system effectively with limited data, which has strong extensibility. We also define a adjacent n-gram pattern to explore potential patterns for dialogue entities. Experimental results show that our approach outperforms the baseline models on most metrics. In the few-shot scenario, we show our method get a great improvement compared with previous methods while keeping smaller model scale.- Anthology ID:
- 2023.findings-acl.194
- 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:
- 3109–3122
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.194
- DOI:
- 10.18653/v1/2023.findings-acl.194
- Cite (ACL):
- Xing Ma, Peng Zhang, and Feifei Zhao. 2023. Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented Dialogue. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3109–3122, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented Dialogue (Ma et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.194.pdf