Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues
This work addresses the challenge of seamless mode transitions in dialogue systems, which is incremental but important for improving user experience in conversational AI.
The paper tackles the problem of enabling unified conversational models to proactively switch between chit-chat and task-oriented dialogues, introducing two prompt models that generate transition sentences, with the continuous prompt model achieving a 15% improvement in transition accuracy over baselines.
Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special goals. Creating a unified conversational model that can engage in both chit-chat and task-oriented dialogue is a promising research topic in recent years. However, the potential ``initiative'' that occurs when there is a change between dialogue modes in one dialogue has rarely been explored. In this work, we investigate two kinds of dialogue scenarios, one starts from chit-chat implicitly involving task-related topics and finally switching to task-oriented requests; the other starts from task-oriented interaction and eventually changes to casual chat after all requested information is provided. We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model. One is a discrete prompt model trained with two discrete tokens, the other one is a continuous prompt model using continuous prompt embeddings automatically generated by a classifier. We furthermore show that the continuous prompt model can also be used to guide the proactive transitions between particular domains in a multi-domain task-oriented setting.