Unsupervised Deep Cross-Language Entity Alignment

TL;DR

This paper introduces an unsupervised deep learning approach for cross-language entity alignment that combines multilingual encoding with bipartite matching, achieving high accuracy without relying on labeled data.

Contribution

It presents a novel unsupervised method using deep multilingual encoders and bipartite matching with ranked results, outperforming state-of-the-art supervised and unsupervised techniques.

Findings

Achieved Hits@1 scores of 0.966, 0.990, 0.996 on DBP15K dataset.

Outperformed existing unsupervised and semi-supervised methods.

Marginally below supervised methods in some language pairs.

Abstract

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.