TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction

Yizhi Li, Wei Fan, Chao Liu, Chenghua Lin, Jiang Qian


Abstract
Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task.One state-of-the-art method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a novel score function TranSHER, which leverages relation-specific translations between head and tail entities to relax the constraint of hyper-ellipsoid restrictions. By introducing an intuitive and simple relation-specific translation, TranSHER can provide more direct guidance on optimization and capture more semantic characteristics of entities with complex relations. Experimental results show that TranSHER achieves state-of-the-art performance on link prediction and generalizes well to datasets in different domains and scales. Our codes are public available athttps://github.com/yizhilll/TranSHER.
Anthology ID:
2022.emnlp-main.583
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8517–8528
Language:
URL:
https://aclanthology.org/2022.emnlp-main.583
DOI:
10.18653/v1/2022.emnlp-main.583
Bibkey:
Cite (ACL):
Yizhi Li, Wei Fan, Chao Liu, Chenghua Lin, and Jiang Qian. 2022. TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8517–8528, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction (Li et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.583.pdf