Previous zero-shot dialogue state tracking (DST) methods only apply transfer
learning, but ignore unlabelled data in the target domain. We transform
zero-shot DST into few-shot DST by utilising such unlabelled data via joint and
self-training methods. Our method incorporates auxiliary tasks that generate
slot types as inverse prompts for main tasks, creating slot values during joint
training. Cycle consistency between these two tasks enables the generation and
selection of quality samples in unknown target domains for subsequent
fine-tuning. This approach also facilitates automatic label creation, thereby
optimizing the training and fine-tuning of DST models. We demonstrate this
method's effectiveness on large language models in zero-shot scenarios,
improving average joint goal accuracy by $8\%$ across all domains in MultiWOZ.

我们将零样本对话状态跟踪转化为少样本对话状态跟踪，通过联合和自我训练方法利用目标域中的无标签数据。该方法通过辅助任务生成槽类型作为主要任务的逆提示，在联合训练期间创建槽值。这两个任务之间的循环一致性使得能够生成和选择未知目标域中的高质量样本，以进行后续的微调。此方法还有助于自动标签创建，从而优化对话状态跟踪模型的训练和微调。我们在零样本场景中的大型语言模型上展示了该方法的有效性，在 MultiWOZ 的所有领域中，平均联合目标准确率提高了 8%。