A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example

TL;DR

This paper introduces a low-cost, controllable, and interpretable task-oriented chatbot framework using Dialogue Actions and TaskFlow, demonstrated effectively on real-world after-sale customer service data.

Contribution

The paper proposes a novel Dialogue Action concept and a tree-structured TaskFlow framework that simplifies ontology construction and enhances control and interpretability.

Findings

Successfully deployed on real-world after-sale services

Reduces developer effort significantly

Maintains key task-oriented functionalities

Abstract

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.