Multi-relation question answering (QA) is a challenging task, where given questions usually require long reasoning chains in KGs that consist of multiple relations. Recently, methods with explicit multi-step reasoning over KGs have been prominently used in this task and have demonstrated promising performance. Examples include methods that perform stepwise label propagation through KG triples and methods that navigate over KG triples based on reinforcement learning. A main weakness of these methods is that their reasoning mechanisms are usually complex and difficult to implement or train. In this paper, we argue that multi-relation QA can be achieved via end-to-end single-step implicit reasoning, which is simpler, more efficient, and easier to adopt. We propose QAGCN -- a Question-Aware Graph Convolutional Network (GCN)-based method that includes a novel GCN architecture with controlled question-dependent message propagation for the implicit reasoning. Extensive experiments have been conducted, where QAGCN achieved competitive and even superior performance compared to state-of-the-art explicit-reasoning methods. Our code and pre-trained models are available in the repository: https://github.com/ruijie-wang-uzh/QAGCN

翻译：多关系问答是一项具有挑战性的任务，给定问题通常需要在包含多个关系的知识图谱上进行长链推理。近期，基于知识图谱的显式多步推理方法在该任务中得到广泛应用并展现出优异性能，例如通过知识图谱三元组进行逐跳标签传播的方法，以及基于强化学习在知识图谱三元组中导航的方法。这些方法的主要缺陷在于其推理机制通常复杂且难以实现或训练。本文提出多关系问答可通过端到端单步隐式推理实现，该方法更简单、高效且易于采用。我们提出QAGCN——一种基于问题感知图卷积网络的方法，该网络采用新型GCN架构，通过受问题控制的依赖关系进行消息传播以实现隐式推理。大量实验表明，与最先进的显式推理方法相比，QAGCN在性能上具有竞争性甚至更优。我们的代码与预训练模型发布于仓库：https://github.com/ruijie-wang-uzh/QAGCN