SEEK: Segmented Embedding of Knowledge Graphs

In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering. However, existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them still far from satisfactory... (read more)

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Link Prediction FB15k SEEK MRR 0.825 # 5
Hits@10 0.886 # 9
Hits@3 0.841 # 3
Hits@1 0.792 # 2
Link Prediction YAGO37 SEEK Hits@1 0.370 # 1
Hits@10 0.622 # 1
Hits@3 0.498 # 1
MRR 0.454 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet