Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph (WG) followed by reasoning using Graph Neural Networks(GNNs). This faces two major challenges: (i) it is difficult to capture all the information from the QA in the WG, and (ii) the WG contains some irrelevant nodes from the KG. To address these, we propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA pair. We evaluate our results on OpenBookQA, CommonsenseQA and MedQA-USMLE and see that GrapeQA shows consistent improvements over its LM + KG predecessor (QA-GNN in particular) and large improvements on OpenBookQA.

翻译：常识问答方法结合了预训练语言模型的能力与知识图谱提供的推理能力。典型方法从知识图谱中收集与问答对相关的节点，构建工作图，随后利用图神经网络进行推理。这面临两大挑战：（i）难以在工作图中捕获问答对的所有信息；（ii）工作图包含来自知识图谱的部分无关节点。为解决这些问题，我们提出GrapeQA，对工作图进行两项简单改进：（i）显式实体图增强：从问答对中识别相关文本片段，并用语言模型的对应潜在表征增强工作图；（ii）上下文感知节点剪枝：移除与问答对关联度较低的节点。我们在OpenBookQA、CommonsenseQA和MedQA-USMLE上评估结果，发现GrapeQA相较于其基于语言模型+知识图谱的前身（特别是QA-GNN）呈现持续改进，并在OpenBookQA上取得大幅提升。