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.

翻译：多关系问答是一项具有挑战性的任务，给定问题通常需要利用知识图谱中由多个关系构成的推理链才能回答。近年来，基于知识图谱的显式多步推理方法在此任务中得到广泛应用，并展现出令人瞩目的性能。例如，通过知识图谱三元组进行逐步标签传播的方法，以及基于强化学习在知识图谱三元组上进行导航的方法。这些方法的主要缺陷在于其推理机制通常较为复杂，实现或训练难度较大。本文论证了多关系问答可以通过端到端的单步隐式推理实现，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隐式推理方法，该方法包含一种新颖的GCN架构，通过受控的问题相关消息传播实现隐式推理。大量实验表明，与最先进的显式推理方法相比，QAGCN取得了具有竞争力甚至更优的性能。