Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
This addresses the challenge of improving conversational AI for more coherent and informative multi-turn dialogues, representing an incremental advance in a specific domain.
The paper tackles the problem of knowledge selection in multi-turn knowledge-grounded dialogues by proposing a difference-aware method that leverages differences between knowledge across turns, resulting in more accurate knowledge selection and more informative responses, significantly outperforming state-of-the-art baselines.
In a multi-turn knowledge-grounded dialog, the difference between the knowledge selected at different turns usually provides potential clues to knowledge selection, which has been largely neglected in previous research. In this paper, we propose a difference-aware knowledge selection method. It first computes the difference between the candidate knowledge sentences provided at the current turn and those chosen in the previous turns. Then, the differential information is fused with or disentangled from the contextual information to facilitate final knowledge selection. Automatic, human observational, and interactive evaluation shows that our method is able to select knowledge more accurately and generate more informative responses, significantly outperforming the state-of-the-art baselines. The codes are available at https://github.com/chujiezheng/DiffKS.