Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.7% from 40.5 to 46.3 on CWQ and 5.8% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.

翻译：知识库问答是一项具有挑战性的任务，旨在从大规模知识库中检索正确答案。现有工作主要聚焦于实体表示和最终答案推理，导致该任务受到有限的监督。此外，作为经验性决定推理路径选择的要素，关系在近期研究中未被充分考虑。本文提出一种新颖框架RE-KBQA，利用知识库中的关系来增强实体表示并引入额外监督。我们从三个维度探索关系引导：首先，采用变分图自编码器学习关系重要性以区分相似实体；其次，通过多任务机制预测关系分布作为软标签，挖掘额外监督信号；最后，设计基于关系引导的重排序算法进行后处理。在两个基准数据集上的实验结果表明，该框架的有效性与优越性：在CWQ上F1分数从40.5提升至46.3（提升5.7%），在WebQSP上从62.8提升至68.5（提升5.8%），性能优于或持平于当前最先进方法。