A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example
This work addresses the problem of building low-cost, controllable chatbots for after-sale services, but it appears incremental as it builds on existing dialogue system concepts.
The paper tackled the bottlenecks of traditional task-oriented dialogue systems, such as difficult ontology construction and poor controllability, by proposing a Dialogue Action and TaskFlow framework, which reduced developer burden effectively in real-world after-sale services.
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.