@inproceedings{sreedhar-parisien-2022-prompt,
    title = "Prompt Learning for Domain Adaptation in Task-Oriented Dialogue",
    author = "Sreedhar, Makesh Narsimhan  and
      Parisien, Christopher",
    editor = "Ou, Zhijian  and
      Feng, Junlan  and
      Li, Juanzi",
    booktitle = "Proceedings of the Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems (SereTOD)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, Beijing (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.seretod-1.4/",
    doi = "10.18653/v1/2022.seretod-1.4",
    pages = "24--30",
    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."
}