Cross-lingual entity alignment is the task of finding the same semantic
entities from different language knowledge graphs. In this paper, we propose a
simple and novel unsupervised method for cross-language entity alignment. We
utilize the deep learning multi-language encoder combined with a machine
translator to encode knowledge graph text, which reduces the reliance on label
data. Unlike traditional methods that only emphasize global or local alignment,
our method simultaneously considers both alignment strategies. We first view
the alignment task as a bipartite matching problem and then adopt the
re-exchanging idea to accomplish alignment. Compared with the traditional
bipartite matching algorithm that only gives one optimal solution, our
algorithm generates ranked matching results which enabled many potentials
downstream tasks. Additionally, our method can adapt two different types of
optimization (minimal and maximal) in the bipartite matching process, which
provides more flexibility. Our evaluation shows, we each scored 0.966, 0.990,
and 0.996 Hits@1 rates on the DBP15K dataset in Chinese, Japanese, and French
to English alignment tasks. We outperformed the state-of-the-art method in
unsupervised and semi-supervised categories. Compared with the state-of-the-art
supervised method, our method outperforms 2.6% and 0.4% in Ja-En and Fr-En
alignment tasks while marginally lower by 0.2% in the Zh-En alignment task.

提出了一种简单且新颖的无监督方法，利用深度学习多语言编码器结合机器翻译器对知识图谱文本进行编码，同时考虑全局与局部对齐策略，并生成排名匹配结果。在跨语言实体对齐任务上，我们的方法在 DBP15K 数据集中的中文、日文和法文到英文对齐任务中得到了较高的准确率，超过了无监督和半监督类别的最新方法。与最新的有监督方法相比，在日文到英文和法文到英文对齐任务中，我们的方法分别提高了 2.6% 和 0.4%，在中文到英文对齐任务中略微降低了 0.2%。

无监督深度跨语言实体对齐

Unsupervised Deep Cross-Language Entity Alignment

Multilingual knowledge graphs (KGs), such as YAGO and DBpedia, represent
entities in different languages. The task of cross-lingual entity alignment is
to match entities in a source language with their counterparts in target
languages. In this work, we investigate embedding-based approaches to encode
entities from multilingual KGs into the same vector space, where equivalent
entities are close to each other. Specifically, we apply graph convolutional
networks (GCNs) to combine multi-aspect information of entities, including
topological connections, relations, and attributes of entities, to learn entity
embeddings. To exploit the literal descriptions of entities expressed in
different languages, we propose two uses of a pretrained multilingual BERT
model to bridge cross-lingual gaps. We further propose two strategies to
integrate GCN-based and BERT-based modules to boost performance. Extensive
experiments on two benchmark datasets demonstrate that our method significantly
outperforms existing systems.

本文研究使用基于嵌入的方法将不同语言的实体编码到同一向量空间中，并提出使用预训练的多语言 BERT 模型来融合各个语言中的实体描述，以寻找源语言和目标语言之间相应实体的方法。结果表明，该方法在两个基准数据集上明显优于现有系统。