论文标题
点或生成对话状态跟踪器
Point or Generate Dialogue State Tracker
论文作者
论文摘要
对话状态跟踪是面向任务的对话系统的关键部分，该系统估计了对话的每个转盘的目标。在本文中，我们提出了点或生成对话州跟踪器（POGD）。 POGD以两个角度解决了对话状态跟踪任务：1）指出从用户的话语中明确表达的插槽值，以及2）基于特定于插槽的上下文产生隐式表示的插槽值。它还共享所有插槽中的参数，这些参数可实现知识共享并获得大规模跨域对话的可扩展性。此外，其子模型的训练过程被制定为多任务学习程序，以进一步促进其泛化能力。实验表明，POGD不仅在WOZ 2.0和Multiwoz 2.0数据集中获得最新的结果，而且对看不见的值和新插槽具有良好的概括。
Dialogue state tracking is a key part of a task-oriented dialogue system, which estimates the user's goal at each turn of the dialogue. In this paper, we propose the Point-Or-Generate Dialogue State Tracker (POGD). POGD solves the dialogue state tracking task in two perspectives: 1) point out explicitly expressed slot values from the user's utterance, and 2) generate implicitly expressed ones based on slot-specific contexts. It also shares parameters across all slots, which achieves knowledge sharing and gains scalability to large-scale across-domain dialogues. Moreover, the training process of its submodules is formulated as a multi-task learning procedure to further promote its capability of generalization. Experiments show that POGD not only obtains state-of-the-art results on both WoZ 2.0 and MultiWoZ 2.0 datasets but also has good generalization on unseen values and new slots.
