Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to classify each candidate snippet as "relevant" or "irrelevant" independently. However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets. Moreover, they lack modeling of the discourse structure of dialogue-knowledge interactions. We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. GenKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogue-knowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.

翻译：知识选择是知识驱动型对话（KGD）中的关键环节，旨在根据对话历史选择适合用于生成回复的知识片段。以往研究主要采用分类方法，将每个候选片段独立归类为“相关”或“不相关”。然而，这类方法忽略了片段间的交互作用，导致难以准确推断片段含义。此外，它们缺乏对对话与知识交互中话语结构的建模能力。我们提出一种简单而有效的生成式知识选择方法GenKS。该方法通过序列到序列模型生成片段标识符来学习选择过程，从而借助注意力机制内在捕获知识内部交互；同时，我们设计超链接机制显式建模对话—知识交互。在三个基准数据集上的实验表明，GenKS在知识选择与回复生成任务上均取得了最优结果。