This paper focuses on end-to-end task-oriented dialogue systems, which jointly handle dialogue state tracking (DST) and response generation. Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus. However, the annotation of the corpus is costly, time-consuming, and cannot cover a wide range of domains in the real world. To solve this problem, we propose a multi-span prediction network (MSPN) that performs unsupervised DST for end-to-end task-oriented dialogue. Specifically, MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords. Based on these keywords, MSPN uses a semantic distance based clustering approach to obtain the values of each slot. In addition, we propose an ontology-based reinforcement learning approach, which employs the values of each slot to train MSPN to generate relevant values. Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements. Besides, we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain, which further demonstrates the adaptability of MSPN.

本文重点关注端到端的面向任务的对话系统，该系统共同处理对话状态跟踪（DST）和响应生成。传统方法通常采用监督范式从手动标记的语料库中学习 DST。然而，语料库的标注成本高昂、耗时，并且无法覆盖现实世界中的广泛领域。为了解决这个问题，我们提出了一种多跨度预测网络（MSPN），它可以对端到端的面向任务的对话执行无监督 DST。具体来说，MSPN 包含一种新颖的拆分合并复制机制，可以捕获对话中的长期依赖关系，以自动提取多个文本范围作为关键字。基于这些关键词，MSPN使用基于语义距离的聚类方法来获得每个槽的值。此外，我们提出了一种基于本体的强化学习方法，该方法利用每个槽的值来训练 MSPN 生成相关值。单域和多域面向任务的对话数据集的实验结果表明，MSPN 实现了最先进的性能，并取得了显着的改进。此外，我们在低资源医学领域构建了一个新的中文对话数据集MeDial，进一步证明了MSPN的适应性。