Entity Alignment (EA) aims to find the equivalent entities between two Knowledge Graphs (KGs). Existing methods usually encode the triples of entities as embeddings and learn to align the embeddings, which prevents the direct interaction between the original information of the cross-KG entities. Moreover, they encode the relational triples and attribute triples of an entity in heterogeneous embedding spaces, which prevents them from helping each other. In this paper, we transform both triples into unified textual sequences, and model the EA task as a bi-directional textual entailment task between the sequences of cross-KG entities. Specifically, we feed the sequences of two entities simultaneously into a pre-trained language model (PLM) and propose two kinds of PLM-based entity aligners that model the entailment probability between sequences as the similarity between entities. Our approach captures the unified correlation pattern of two kinds of information between entities, and explicitly models the fine-grained interaction between original entity information. The experiments on five cross-lingual EA datasets show that our approach outperforms the state-of-the-art EA methods and enables the mutual enhancement of the heterogeneous information. Codes are available at https://github.com/OreOZhao/TEA.

翻译：实体对齐（Entity Alignment, EA）旨在发现两个知识图谱（Knowledge Graphs, KGs）中的等价实体。现有方法通常将实体的三元组编码为嵌入表示并学习对齐这些嵌入，这阻碍了跨知识图谱实体原始信息之间的直接交互。此外，这些方法将实体的关系三元组和属性三元组编码到异构的嵌入空间中，导致两者无法相互促进。本文中，我们将两种三元组统一转换为文本序列，并将实体对齐任务建模为跨知识图谱实体序列之间的双向文本蕴涵任务。具体而言，我们将两个实体的序列同时输入预训练语言模型（Pre-trained Language Model, PLM），并提出了两种基于PLM的实体对齐器，通过建模序列之间的蕴涵概率来衡量实体间的相似度。该方法能够捕捉实体间两类信息的统一关联模式，并显式建模原始实体信息之间的细粒度交互。在五个跨语言实体对齐数据集上的实验表明，我们的方法优于最先进的实体对齐方法，并实现了异构信息的相互增强。相关代码已开源至 https://github.com/OreZhao/TEA。