Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model
Open paper
Benchmark
Model
Rank
Results
entity-typing-on-ontonotes-v5-english
MLMET
#1
F1: 49.1
Precision: 53.6
Recall: 45.3
entity-typing-on-open-entity
MLMET
#6
F1: 49.1
Rank counts only results with a code link.