UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues

TL;DR

UniDS is a unified dialogue system capable of handling both chit-chat and task-oriented conversations, demonstrating comparable or superior performance and improved robustness over specialized systems.

Contribution

The paper introduces a unified dialogue data schema and training method that enables a single system to perform both dialogue types without extra parameters.

Findings

UniDS performs comparably to pure chit-chat systems.

UniDS outperforms state-of-the-art task-oriented systems.

UniDS exhibits better robustness and seamless switching between dialogue types.

Abstract

With the advances in deep learning, tremendous progress has been made with chit-chat dialogue systems and task-oriented dialogue systems. However, these two systems are often tackled separately in current methods. To achieve more natural interaction with humans, a dialogue agent needs to be capable of both chatting and accomplishing tasks. To this end, we propose a unified dialogue system (UniDS) with the two aforementioned skills. In particular, we design a unified dialogue data schema, compatible for both chit-chat and task-oriented dialogues, and we train UniDS with mixed dialogue data from a pretrained chit-chat dialogue model. Without adding extra parameters to SOTA baselines, UniDS can alternatively handle chit-chat and task-oriented dialogues in a unified framework. Experimental results demonstrate that the proposed UniDS works comparably well as the pure chit-chat system, and it outperforms state-of-the-art task-oriented dialogue systems. More importantly, UniDS achieves better robustness as it is able to smoothly switch between two types of dialogues. These results demonstrate the feasibility and potential of building an one-for-all dialogue system.