From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

TL;DR

This paper introduces SEU, a simple and effective unsupervised method for cross-lingual entity alignment that outperforms supervised methods and improves efficiency and interpretability by transforming the problem into an assignment task.

Contribution

The paper proposes a novel neural network-free approach for cross-lingual entity alignment by leveraging the isomorphic assumption, simplifying the problem into an assignment task.

Findings

SEU outperforms supervised methods on public datasets.

SEU is more efficient and interpretable than neural network-based methods.

The approach demonstrates high stability across experiments.

Abstract

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. Meanwhile, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNNbased methods, we successfully transform the cross-lingual EA problem into the assignment problem. Based on this finding, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments show that our proposed unsupervised method even beats advanced supervised methods across all public datasets and has high efficiency, interpretability, and stability.