Knowing the No-match: Entity Alignment with Dangling Cases

Zequn Sun, Muhao Chen, Wei Hu


Abstract
This paper studies a new problem setting of entity alignment for knowledge graphs (KGs). Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities. As the first attempt to this problem, we construct a new dataset and design a multi-task learning framework for both entity alignment and dangling entity detection. The framework can opt to abstain from predicting alignment for the detected dangling entities. We propose three techniques for dangling entity detection that are based on the distribution of nearest-neighbor distances, i.e., nearest neighbor classification, marginal ranking and background ranking. After detecting and removing dangling entities, an incorporated entity alignment model in our framework can provide more robust alignment for remaining entities. Comprehensive experiments and analyses demonstrate the effectiveness of our framework. We further discover that the dangling entity detection module can, in turn, improve alignment learning and the final performance. The contributed resource is publicly available to foster further research.
Anthology ID:
2021.acl-long.278
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3582–3593
Language:
URL:
https://aclanthology.org/2021.acl-long.278
DOI:
10.18653/v1/2021.acl-long.278
Bibkey:
Cite (ACL):
Zequn Sun, Muhao Chen, and Wei Hu. 2021. Knowing the No-match: Entity Alignment with Dangling Cases. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3582–3593, Online. Association for Computational Linguistics.
Cite (Informal):
Knowing the No-match: Entity Alignment with Dangling Cases (Sun et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.278.pdf
Video:
 https://aclanthology.org/2021.acl-long.278.mp4
Code
 nju-websoft/OpenEA
Data
DBP2.0 zh-en