Integrating Pre-trained Model into Rule-based Dialogue Management

TL;DR

This paper presents a hybrid dialogue management approach that combines rule-based and pre-trained data-driven models, enhancing scalability, interpretability, and few-shot learning capabilities for industrial task-oriented dialogue systems.

Contribution

It introduces a novel 'model-trigger' design for trainability and integrates pre-trained models to improve few-shot learning in rule-based dialogue management.

Findings

Effective in complex scenario handling

Strong few-shot learning performance

Maintains interpretability of dialogue management

Abstract

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility. However, it is hard for developers to maintain the dialogue logic when the scenarios get more and more complex. On the other hand, data-driven dialogue systems, usually with end-to-end structures, are popular in academic research and easier to deal with complex conversations, but such methods require plenty of training data and the behaviors are less interpretable. In this paper, we propose a method to leverages the strength of both rule-based and data-driven dialogue managers (DM). We firstly introduce the DM of Carina Dialog System (CDS, an advanced industrial dialogue system built by Microsoft). Then we propose the "model-trigger" design to make the DM trainable thus scalable to scenario changes. Furthermore, we integrate pre-trained models and empower the DM with few-shot capability. The experimental results demonstrate the effectiveness and strong few-shot capability of our method.