Entity Alignment (EA) aims to match equivalent entities in different Knowledge Graphs (KGs), which is essential for knowledge fusion and integration. Recently, embedding-based EA has attracted significant attention and many approaches have been proposed. Early approaches primarily focus on learning entity embeddings from the structural features of KGs, defined by relation triples. Later methods incorporated entities' names and attributes as auxiliary information to enhance embeddings for EA. However, these approaches often used different techniques to encode structural and attribute information, limiting their interaction and mutual enhancement. In this work, we propose a dense entity retrieval framework for EA, leveraging language models to uniformly encode various features of entities and facilitate nearest entity search across KGs. Alignment candidates are first generated through entity retrieval, which are subsequently reranked to determine the final alignments. We conduct comprehensive experiments on both cross-lingual and monolingual EA datasets, demonstrating that our approach achieves state-of-the-art performance compared to existing EA methods.

翻译：实体对齐（EA）旨在匹配不同知识图谱（KG）中的等价实体，这对知识融合与集成至关重要。近年来，基于嵌入的实体对齐方法受到广泛关注，已有多种技术被提出。早期方法主要侧重于从知识图谱的结构特征（即关系三元组）中学习实体嵌入。后续方法则引入实体名称与属性作为辅助信息，以增强实体对齐的嵌入表示。然而，这些方法通常采用不同技术分别编码结构信息与属性信息，限制了二者之间的交互与相互增强。本研究提出一种基于密集实体检索的实体对齐框架，利用语言模型统一编码实体的多维度特征，并实现跨知识图谱的最近邻实体搜索。对齐候选首先通过实体检索生成，随后经过重排序以确定最终对齐结果。我们在跨语言与单语言实体对齐数据集上进行了全面实验，结果表明相较于现有实体对齐方法，本方法取得了最先进的性能。