Contextual Parameter Generation for Knowledge Graph Link Prediction

We consider the task of knowledge graph link prediction. Given a question consisting of a source entity and a relation (e.g., Shakespeare and BornIn), the objective is to predict the most likely answer entity (e.g., England)... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Link Prediction FB15k-237 CoPER-ConvE MRR .4256 # 5
Hits@10 .6292 # 2
Hits@1 .3218 # 4
Link Prediction NELL-995 CoPER-ConvE MRR .7868 # 1
Hits@1 .7215 # 1
Hits@10 .8835 # 1
Link Prediction WN18RR CoPER-ConvE MRR .4833 # 13
Hits@10 .5612 # 17
Hits@1 .4405 # 11

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