The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority of the slots in each turn should simply inherit the slot values from the previous turn. Therefore, the mechanism of treating slots equally in each turn not only is inefficient but also may lead to additional errors because of the redundant slot value generation. To address this problem, we devise the two-stage DSS-DST which consists of the Dual Slot Selector based on the current turn dialogue, and the Slot Value Generator based on the dialogue history. The Dual Slot Selector determines each slot whether to update slot value or to inherit the slot value from the previous turn from two aspects: (1) if there is a strong relationship between it and the current turn dialogue utterances; (2) if a slot value with high reliability can be obtained for it through the current turn dialogue. The slots selected to be updated are permitted to enter the Slot Value Generator to update values by a hybrid method, while the other slots directly inherit the values from the previous turn. Empirical results show that our method achieves 56.93%, 60.73%, and 58.04% joint accuracy on MultiWOZ 2.0, MultiWOZ 2.1, and MultiWOZ 2.2 datasets respectively and achieves a new state-of-the-art performance with significant improvements.
翻译:对话框状态跟踪( DST) 的目标是预测所有先前对话背景下的当前对话状态 。 现有方法通常从头开始预测对话状态。 但是, 每个回合中绝大多数的空档应该只继承上一个回合的空档值。 因此, 每一个回合中平等处理空档的机制不仅效率低下, 而且由于冗余的空档值生成, 可能导致更多错误。 为了解决这个问题, 我们设计了两个阶段的 DSS- DST, 包括基于当前转折对话框的双点值选择器和基于对话历史的 Slot 值生成器。 双层 Slot 选择器决定每个空档是更新空档值还是从上一个回合中继承空档值。 从两个方面看:(1) 如果每个回合中平等处理空档的机制不仅效率不高, 而且由于生成了多余的空档值, 可能会导致额外的错误。 为了解决这个问题, 我们所选择的两阶段都允许以混合方式进入 Slot 值生成器来更新价值观, 而其他空档则直接继承前一个回合的值。 Empricalal res 和 MUIZ 分别显示我们的方法实现了显著的进度, 21% 和多级 。