论文标题
通过推理重新思考对话状态跟踪
Rethinking Dialogue State Tracking with Reasoning
论文作者
论文摘要
跟踪对话指出，以更好地解释用户目标，而下游政策学习是对话管理中的瓶颈。普遍的做法是将其视为将对话内容分类为一组预定义的插槽配对的问题，或者给定对话历史记录为不同的插槽生成值。两者都对考虑对话中发生的依赖关系有局限性，并且缺乏推理能力。本文提议在后端数据的帮助下，通过对话的推理逐渐跟踪对话状态。经验结果表明，就多种域中的大规模人类对话数据集而言，我们的方法在共同信念准确性方面显着优于最先进的方法。
Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human-human dialogue dataset across multiple domains.
