Abstract
Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual 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.- Anthology ID:
- 2021.emnlp-main.226
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2843–2853
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.226
- DOI:
- 10.18653/v1/2021.emnlp-main.226
- Cite (ACL):
- Xin Mao, Wenting Wang, Yuanbin Wu, and Man Lan. 2021. From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2843–2853, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment (Mao et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2021.emnlp-main.226.pdf
- Code
- maoxinn/seu
- Data
- DBP15K, MMKG