Commonsense question answering has demonstrated considerable potential across various applications like assistants and social robots. Although fully fine-tuned pre-trained Language Models(LM) have achieved remarkable performance in commonsense reasoning, their tendency to excessively prioritize textual information hampers the precise transfer of structural knowledge and undermines interpretability. Some studies have explored combining LMs with Knowledge Graphs(KGs) by coarsely fusing the two modalities to perform Graph Neural Network(GNN)-based reasoning that lacks a profound interaction between heterogeneous modalities. In this paper, we propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP, aiming to maintain a balance between heterogeneous knowledge and enhance the cross-modal interaction within the LM+GNNs model. In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary to boost the performance. Afterward, a structure-aware frozen PLM is employed to fully incorporate the structured and textual information from the evidence graph, where the generation of prompts is driven by graph entities and relations. Finally, a heterogeneous message-passing reasoning module is used to facilitate deep interaction of knowledge between the LM and graph-based networks. Empirical validation, conducted through extensive experiments on three benchmark datasets, demonstrates the notable performance of the proposed model. The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.

翻译：常识问答已在诸多应用（如智能助手与社交机器人）中展现出显著潜力。尽管基于完全微调预训练语言模型的方法在常识推理中取得了卓越性能，但其过度侧重文本信息的倾向阻碍了结构知识的精确迁移，并削弱了模型可解释性。部分研究尝试通过粗粒度融合语言模型与知识图谱来执行基于图神经网络的推理，但这种异构模态间的交互仍缺乏深度。本文提出一种新颖的基于图结构的感知提示学习模型G-SAP，旨在平衡异构知识并增强语言模型与图神经网络模型间的跨模态交互。具体而言，我们首先通过整合ConceptNet、维基百科与剑桥词典等多源知识构建证据图以提升性能；随后，采用结构感知的冻结预训练语言模型充分融合证据图中的结构化信息与文本信息，其中提示生成由图实体与关系驱动；最后，通过异构消息传递推理模块促进语言模型与图网络之间的深度知识交互。在三个基准数据集上的大量实验验证了所提模型的卓越性能。结果表明，该模型相较于现有方法取得显著进步——尤其在OpenbookQA数据集上，较当前最优的语言模型-图神经网络模型实现了6.12%的性能提升。