Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraphrases improves the model robustness to these variations but can be either costly or difficult to control. We propose to circumvent these issues by grounding the state tracking model in knowledge-seeking turns collected from the dialogue corpus as well as the schema. Including these turns in prompts during finetuning and inference leads to marked improvements in model robustness, as demonstrated by large average joint goal accuracy and schema sensitivity improvements on SGD and SGD-X.

翻译：模式引导的对话状态追踪器无需额外训练即可泛化至新领域，但其性能易受模式编写风格的影响。通过人工或合成模式释义扩充训练集可提升模型对此类变体的鲁棒性，但这种方式成本高昂或难以控制。我们提出通过将对话语料库中收集的知识获取轮次与模式共同作为状态追踪模型的基座来解决上述问题。在微调和推理过程中将这些轮次融入提示（prompts），能显著提升模型鲁棒性——在SGD和SGD-X数据集上，平均联合目标准确率和模式敏感度的大幅改善充分证明了这一点。