论文标题
在几次对话状态跟踪中的文本学习
In-Context Learning for Few-Shot Dialogue State Tracking
论文作者
论文摘要
收集和注释以任务为导向的对话是耗时且昂贵的。因此，零和很少的射击学习可以极大地使对话状态跟踪（DST）受益。在这项工作中，我们为零射击和少量学习DST提出了一个内在学习框架（ICL）框架，其中大型的预训练的语言模型（LM）采用测试实例，并将一些示例作为输入，并直接解码对话状态而无需任何参数更新。为了更好地利用LM提示中的表格域描述，我们将DST重新制定为文本到SQL问题。我们还提出了一种新颖的方法来检索带注释的对话作为示例。 Multiwoz上的经验结果表明，我们的方法IC-DST在几个射击设置中大大优于先前的微调最新模型。此外，我们在零拍设置中测试IC-DST，其中模型仅将固定的任务指令作为输入，发现它的表现优于先前的零射击方法，而不是很大。
Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin.
