Prompt Learning for Domain Adaptation in Task-Oriented Dialogue
Makesh Narsimhan Sreedhar, Christopher Parisien · 2022
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.