VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding
Open paper
Benchmark
Model
Rank
Results
citation-intent-classification-on-acl-arc
VarMAE
–
Macro-F1: Not reported
Micro-F1: 76.50
participant-intervention-comparison-outcome-extraction-on-ebm-nlp
VarMAE
–
F1: 76.01
Rank counts only results with a code link.