Jiang Qian


2022

pdf bib
TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction
Yizhi Li | Wei Fan | Chao Liu | Chenghua Lin | Jiang Qian
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

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 at https://github.com/yizhilll/TranSHER.