论文标题
差异知识的知识选择，以知识的对话生成
Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
论文作者
论文摘要
在一个多转向知识的对话框中，在不同回合中选择的知识之间的差异通常为知识选择提供了潜在的线索，这在先前的研究中已被很大程度上忽略了。在本文中，我们提出了一种差异感知的知识选择方法。它首先计算在当前回合时提供的候选知识句子与前一轮中选择的候选知识句子之间的差异。然后，差异信息与上下文信息融合或分离以促进最终知识选择。自动，人类的观察和交互式评估表明，我们的方法能够更准确地选择知识并产生更有信息的响应，从而大大优于最先进的基线。这些代码可在https://github.com/chujiezheng/diffks上找到。
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.
