KETOD: Knowledge-Enriched Task-Oriented Dialogue

Anonymous

Abstract: Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat separately. Towards building a human-like assistant that can converse naturally and seamlessly with users, the system needs to be able to conduct both types of conversations effectively. In this work, we investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model. To this end, we create a new dataset, KETOD (Knowledge-Enriched Task-Oriented Dialogue), where we naturally enrich task-oriented dialogue with chit-chats based on relevant entity knowledge. We also propose two new models, SimpleToDPlus and Combiner, for the proposed task. Experimental results on both automatic and human evaluations show that the proposed methods can significantly improve the performance in knowledge-enriched response generation while maintaining a competitive task-oriented dialog performance. We believe our new dataset will be a valuable resource for future studies. We will make the code and the dataset publicly available upon acceptance.