KETOD: Knowledge-Enriched Task-Oriented Dialogue
This work addresses the challenge of creating seamless conversational AI for users by bridging separate dialogue domains, though it is incremental in combining existing approaches.
The authors tackled the problem of integrating task-oriented dialogue and knowledge-grounded chit-chat into a single model to build more human-like assistants, resulting in significant improvements in knowledge-enriched response generation while maintaining competitive task-oriented performance as shown in experiments.
Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a dialogue system that conducts 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 dialogues with chit-chat 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. Our dataset and code are publicly available at \url{https://github.com/facebookresearch/ketod}.