TY - GEN
T1 - From Alignment to Assignment
T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
AU - Mao, Xin
AU - Wang, Wenting
AU - Wu, Yuanbin
AU - Lan, Man
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - Cross-lingual entity alignment (EA) aims to find the equivalent entities between cross-lingual KGs (Knowledge Graphs), 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. However, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNN-based methods, we successfully transform the cross-lingual EA problem into an assignment problem. Based on this re-definition, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments have been conducted to show that our proposed unsupervised approach even beats advanced supervised methods across all public datasets while having high efficiency, interpretability, and stability.
AB - Cross-lingual entity alignment (EA) aims to find the equivalent entities between cross-lingual KGs (Knowledge Graphs), 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. However, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNN-based methods, we successfully transform the cross-lingual EA problem into an assignment problem. Based on this re-definition, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments have been conducted to show that our proposed unsupervised approach even beats advanced supervised methods across all public datasets while having high efficiency, interpretability, and stability.
UR - https://www.scopus.com/pages/publications/85127047081
U2 - 10.18653/v1/2021.emnlp-main.226
DO - 10.18653/v1/2021.emnlp-main.226
M3 - 会议稿件
AN - SCOPUS:85127047081
T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 2843
EP - 2853
BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
Y2 - 7 November 2021 through 11 November 2021
ER -