EchoEA：实体与实体对齐关系之间的回显信息
EchoEA: Echo Information between Entities and Relations for Entity Alignment
摘要：
实体对齐在多源知识图谱的自动集成中起着重要的作用。基于图神经网络（GNN）的最新方法从关系信息中获得实体表示，并取得了可喜的成果。此外，越来越多的方法引入半监督，要求更多的标记训练数据。然而，在基于GNN的EA方法中仍然存在两个挑战：（1）更深的GNN编码器：当前方法的GNN编码器具有有限的深度（通常为2层）。(2)低质量Bootstrapping：生成的半监督数据质量较低。在本文中，我们提出了一个新的框架，回声实体对齐（EchoEA），它利用4级自我注意力机制，实体信息传播到关系和回声回实体。此外，我们提出了属性组合的双向全局过滤策略（ABGS），以改善自举，减少假样本，并产生高质量的训练数据。在三个真实世界的跨语言数据集上的实验结果是稳定的，平均在96%左右，在hits@1，表明我们的方法不仅显着优于最先进的基于GNN的方法，但也是通用的和可转移的现有的EA方法。
英文摘要：
Entity alignment (EA) plays an important role in automatically integrating knowledge graphs (KGs) from multiple sources. Recent approaches based on Graph Neural Network (GNN) obtain entity representation from relation information and have achieved promising results. Besides, more and more methods introduce semi-supervision to ask for more labeled training data. However, two challenges still exist in GNN-based EA methods: (1) Deeper GNN Encoder: The GNN encoder of current methods has limited depth (usually 2-layers). (2) Low-quality Bootstrapping: The generated semi-supervised data is of low quality. In this paper, we propose a novel framework, Echo Entity Alignment (EchoEA), which leverages 4-levels self-attention mechanism to spread entity information to relations and echo back to entities. Furthermore, we propose attribute-combined bi-directional global-filtered strategy (ABGS) to improve bootstrapping, reduce false samples and generate high-quality training data. The experimental results on three real-world cross-lingual datasets are stable at around 96\% at hits@1 on average, showing that our approach not only significantly outperforms the state-of-the-art GNN-based methods, but also is universal and transferable for existing EA methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
