Though widely used in industry, traditional task-oriented dialogue systems suffer from three bottlenecks: (i) difficult ontology construction (e.g., intents and slots); (ii) poor controllability and interpretability; (iii) annotation-hungry. In this paper, we propose to represent utterance with a simpler concept named Dialogue Action, upon which we construct a tree-structured TaskFlow and further build task-oriented chatbot with TaskFlow as core component. A framework is presented to automatically construct TaskFlow from large-scale dialogues and deploy online. Our experiments on real-world after-sale customer services show TaskFlow can satisfy the major needs, as well as reduce the developer burden effectively.

翻译：虽然传统面向任务的对话系统在工业中广泛使用,但有三个瓶颈:(一) 难以建立本体学(例如意图和空档);(二) 控制性和可解释性差;(三) 注释性-饥饿。我们提议在本文件中表述一个更简单的概念,称为“对话行动”,据此我们建造一个树型任务拖车,并进一步建造以任务为导向的聊天室,将任务拖车作为核心组成部分。提出一个框架,以自动建造大型对话的“任务拖车”,并在线部署。我们在现实世界的售后客户服务的实验显示,任务拖车能够满足主要需求,并有效减轻开发者的负担。