Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \textit{cross-task} knowledge from general question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle "none" value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.
翻译:零光传输学习用于对话状态跟踪( DST) 使我们能够处理各种任务导向的对话领域,而无需花费收集内部数据。 在这项工作中,我们提议将普通问题回答( QA) Corbora 的知识从零光 DST 任务的一般问题解答( QA) 中转移。 具体地说,我们提议了可转让的可转让基因质变QA模式,即通过文本到文本的变压器框架将采掘QA和多选择QA无缝地结合起来,并跟踪DST 的绝对空档和非分类空档。 此外,我们提出了两种有效的方法来构建无法解答的问题, 即负面问题取样和背景变速, 使我们的模型能够处理零光点 DST 设置中的“ 无” 值位。 广泛的实验表明, 我们的方法大大改进了Multy QA 和多Woz 上的现有零光点结果。 此外, 与经过充分训练的Schema-Guid 对话框数据集基线相比, 我们的方法在无形域中表现出更好的一般化能力。