BoxE: A Box Embedding Model for Knowledge Base Completion

Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB). A promising approach for KBC is to embed knowledge into latent spaces and make predictions from learned embeddings... (read more)

PDF Abstract NeurIPS 2020 PDF NeurIPS 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Link Prediction FB15k-237 BoxE MRR 0.337 # 27
Hits@10 0.538 # 17
Hits@1 0.238 # 24
Link Prediction FB-AUTO BoxE MRR 0.844 # 1
Hits@10 0.898 # 1
Hits@1 0.814 # 1
Link Prediction JF17K BoxE MRR 0.560 # 2
Hit@1 0.472 # 2
Hit@10 0.722 # 2
Link Prediction YAGO3-10 BoxE MRR 0.567 # 5
Hits@10 0.699 # 4
Hits@1 0.494 # 4

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