论文标题
twirgcn：暂时加权的图形卷积，以回答时间知识图
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
论文作者
论文摘要
近年来，人们对关于知识图（kg）的时间推理（kg）的复杂问题回答（QA）见证了很大的兴趣，但人类能力仍然存在很大的差距。我们探讨了如何概括时间kgqa的关系图卷积网络（RGCN）。具体而言，我们提出了一种新颖，直观且可解释的方案，以根据其相关时间段与问题的相关性调节在卷积期间通过kg边缘传递的消息。我们还引入了一个门控装置，以预测复杂的时间问题的答案是否可能是kg实体或时间，并使用此预测来指导我们的评分机制。我们评估了最终发布的最终发布的系统，该系统是最近发布的，挑战多跳复合时间QA的数据集。我们表明，在不同问题类型上，TwirGCN在该数据集上的最先进系统大大优于最先进的系统。值得注意的是，对于最困难的序数和隐性问题类型，TwirGCN将精度提高了9--10个百分点。
Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabilities. We explore how to generalize relational graph convolutional networks (RGCN) for temporal KGQA. Specifically, we propose a novel, intuitive and interpretable scheme to modulate the messages passed through a KG edge during convolution, based on the relevance of its associated time period to the question. We also introduce a gating device to predict if the answer to a complex temporal question is likely to be a KG entity or time and use this prediction to guide our scoring mechanism. We evaluate the resulting system, which we call TwiRGCN, on TimeQuestions, a recently released, challenging dataset for multi-hop complex temporal QA. We show that TwiRGCN significantly outperforms state-of-the-art systems on this dataset across diverse question types. Notably, TwiRGCN improves accuracy by 9--10 percentage points for the most difficult ordinal and implicit question types.
