With the demanding need for deploying dialogue systems in new domains with less cost, zero-shot dialogue state tracking (DST), which tracks user's requirements in task-oriented dialogues without training on desired domains, draws attention increasingly. Although prior works have leveraged question-answering (QA) data to reduce the need for in-domain training in DST, they fail to explicitly model knowledge transfer and fusion for tracking dialogue states. To address this issue, we propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation, based on a T5 pre-trained language model. Specifically, CoFunDST selects highly-relevant choices to the reference context and fuses them to initialize the decoder to constrain the model outputs. Our experimental results show that our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1. Extensive analyses demonstrate the effectiveness of our proposed approach for improving zero-shot DST learning from QA.
翻译:由于在成本较低、零点对话状态跟踪(DST)的新领域部署对话系统的要求很高,这种系统在不进行理想领域培训的情况下跟踪用户在面向任务的对话中的要求,因此日益引起注意。虽然以前的工作利用了问答(QA)数据来减少对DST内部培训的需要,但是它们没有明确地为跟踪对话状态而进行知识转让和融合的模型。为了解决这一问题,我们提议CoFunDST,它接受关于域名的QA数据集的培训,并直接利用时间档价值候选人选择作为零点对话状态生成的知识,以T5预先培训的语言模式为基础。具体地说,CoFunDST选择了与参考环境高度相关的选择,并结合了这些数据来启动解码器以限制模式产出。我们的实验结果显示,我们提议的模型比多WOZ 2.1中大多数领域现有的零点DST方法,已经超过了联合目标精确度。广泛的分析表明我们提出的改进QA中零点DST学习的方法的有效性。</s>