Abstract
Conversation designers continue to face significant obstacles when creating productionquality task-oriented dialogue systems. The complexity and cost involved in schema development and data collection is often a major barrier for such designers, limiting their ability to create natural, user-friendly experiences. We frame the classification of user intent as the generation of a canonical form, a lightweight semantic representation using natural language. We show that canonical forms offer a promising alternative to traditional methods for intent classification. By tuning soft prompts for a frozen large language model, we show that canonical forms generalize very well to new, unseen domains in a zero- or few-shot setting. The method is also sample-efficient, reducing the complexity and effort of developing new task-oriented dialogue domains.- Anthology ID:
- 2022.seretod-1.4
- Volume:
- Proceedings of the Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems (SereTOD)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, Beijing (Hybrid)
- Editors:
- Zhijian Ou, Junlan Feng, Juanzi Li
- Venue:
- SereTOD
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 24–30
- Language:
- URL:
- https://aclanthology.org/2022.seretod-1.4
- DOI:
- 10.18653/v1/2022.seretod-1.4
- Cite (ACL):
- Makesh Narsimhan Sreedhar and Christopher Parisien. 2022. Prompt Learning for Domain Adaptation in Task-Oriented Dialogue. In Proceedings of the Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems (SereTOD), pages 24–30, Abu Dhabi, Beijing (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Prompt Learning for Domain Adaptation in Task-Oriented Dialogue (Sreedhar & Parisien, SereTOD 2022)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2022.seretod-1.4.pdf