Relation extraction aims at identifying semantic relations between pairs of named entities from unstructured texts and is considered an essential prerequisite for many downstream tasks in natural language processing (NLP). Owing to the ability in expressing complex relationships and interdependency, graph neural networks (GNNs) have been gradually used to solve the relation extraction problem and have achieved state-of-the-art results. However, the designs of GNN-based relation extraction methods are mostly based on empirical intuition, heuristic, and experimental trial-and-error. A clear understanding of why and how GNNs perform well in relation extraction tasks is lacking. In this study, we investigate three well-known GNN-based relation extraction models, CGCN, AGGCN, and SGCN, and aim to understand the underlying mechanisms of the extractions. In particular, we provide a visual analytic to reveal the dynamics of the models and provide insight into the function of intermediate convolutional layers. We determine that entities, particularly subjects and objects in them, are more important features than other words for relation extraction tasks. With various masking strategies, the significance of entity type to relation extraction is recognized. Then, from the perspective of the model architecture, we find that graph structure modeling and aggregation mechanisms in GCN do not significantly affect the performance improvement of GCN-based relation extraction models. The above findings are of great significance in promoting the development of GNNs. Based on these findings, an engineering oriented MLP-based GNN relation extraction model is proposed to achieve a comparable performance and greater efficiency.

关系提取旨在识别非结构化文本中的命名实体对之间的语义关系，被认为是自然语言处理 (NLP) 中许多下游任务的重要先决条件。由于具有表达复杂关系和相互依赖关系的能力，图神经网络（GNN）已逐渐用于解决关系提取问题，并取得了最先进的结果。然而，基于 GNN 的关系提取方法的设计大多基于经验直觉、启发式和实验试错。目前缺乏对 GNN 在关系提取任务中表现良好的原因和方式的清晰理解。在本研究中，我们研究了三种著名的基于 GNN 的关系提取模型：CGCN、AGGCN 和 SGCN，旨在了解提取的潜在机制。特别是，我们提供了视觉分析来揭示模型的动态并深入了解中间卷积层的功能。我们确定实体，特别是其中的主体和客体，对于关系提取任务来说是比其他词更重要的特征。通过各种屏蔽策略，实体类型对关系提取的重要性得到了认可。然后，从模型架构的角度来看，我们发现GCN中的图结构建模和聚合机制并没有显着影响基于GCN的关系提取模型的性能提升。上述发现对于促进GNN的发展具有重要意义。基于这些发现，提出了一种面向工程的基于 MLP 的 GNN 关系提取模型，以实现可比较的性能和更高的效率。