Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation

2020/09/20 by Chujie Zheng, Zheng, Chujie, Yunbo Cao +5
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.2009.09378

Accepted to Findings of EMNLP 2020 (Long Paper)

arxiv created 2020/09/20 · arxiv updated 2020/09/22

Abstract

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.

Related

• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
• Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue
• There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning
• Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
• Generative Knowledge Selection for Knowledge-Grounded Dialogues