The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex documents and integrate it to perform correct responses without the aid of an explicit semantic structure. To address these issues, we propose a novel graph structure, Grounded Graph ($G^2$), that models the semantic structure of both dialogue and knowledge to facilitate knowledge selection and integration for knowledge-grounded dialogue generation. We also propose a Grounded Graph Aware Transformer ($G^2AT$) model that fuses multi-forms knowledge (both sequential and graphic) to enhance knowledge-grounded response generation. Our experiments results show that our proposed model outperforms the previous state-of-the-art methods with more than 10\% gains in response generation and nearly 20\% improvement in factual consistency. Further, our model reveals good generalization ability and robustness. By incorporating semantic structures as prior knowledge in deep neural networks, our model provides an effective way to aid language generation.

翻译：知识驱动对话任务旨在生成能够传递给定知识文档信息的回复。然而，当前基于序列的模型在缺乏显式语义结构辅助的情况下，难以从复杂文档中获取知识并将其整合以生成正确回复。针对这些问题，我们提出了一种新型图结构——基础图（$G^2$），该结构对对话与知识的语义结构进行建模，以促进知识驱动对话生成中的知识选择与整合。同时，我们提出了一种基础图感知Transformer（$G^2AT$）模型，该模型融合了多种形式的知识（序列知识与图结构知识），以增强知识驱动的回复生成。实验结果表明，我们的模型在回复生成任务上相较此前最优方法提升超过10%，在事实一致性上提升近20%。此外，该模型展现出良好的泛化能力与鲁棒性。通过将语义结构作为先验知识引入深度神经网络，我们的模型为辅助语言生成提供了一种有效途径。