Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, few-shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST), where a large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates. This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios. We study ways to formulate dialogue context into prompts for LMs and propose an efficient approach to retrieve dialogues as exemplars given a test instance and a selection pool of few-shot examples. To better leverage the pre-trained LMs, we also reformulate DST into a text-to-SQL problem. Empirical results on MultiWOZ 2.1 and 2.4 show that our method IC-DST outperforms previous fine-tuned state-of-the-art models in few-shot settings.

本研究提出了一个基于in-context learning (ICL)框架、利用大型预训练语言模型 (LM)进行零样本和小样本学习的对话状态跟踪 (DST)方法，重点是通过将DST优化为文本到SQL问题和使用新颖的对话检索方法，以检索标注对话作为样本来提高对答案问题的准确性。在MultiWOZ上的实证结果表明，IC-DST法在小样本情境中明显优于以往最先进的模型，在只输入固定任务指令的零样本情境下，也比以往的零样本方法表现得更好。

少量样本对话状态跟踪的上下文学习