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.
@article{arxiv.2205.06436,
title = {A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example},
author = {Xiangyu Xi and Chenxu Lv and Yuncheng Hua and Wei Ye and Chaobo Sun and Shuaipeng Liu and Fan Yang and Guanglu Wan},
journal= {arXiv preprint arXiv:2205.06436},
year = {2022}
}