Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
This work addresses the problem of generating diverse, knowledge-grounded dialogues for conversational AI, though it appears incremental as it builds on existing pre-trained models and knowledge bases.
The paper tackles the challenge of leveraging background knowledge in open-domain conversational systems by combining knowledge bases with pre-trained models to create a knowledge-driven conversation system. The system achieved state-of-the-art performance through experiments on factors like topic recall algorithms and knowledge choices.
In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that contain real knowledge. In this paper, we combine the knowledge bases and pre-training model to propose a knowledge-driven conversation system. The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation. Based on this system, we study the performance factors that maybe affect the generation of knowledge-driven dialogue: topic coarse recall algorithm, number of knowledge choices, generation model choices, etc., and finally made the system reach state-of-the-art. These experimental results will provide some guiding significance for the future research of this task. As far as we know, this is the first work to study and analyze the effects of the related factors.