|
gptkbp:instance_of
|
gptkb:Performance_Monitoring
|
|
gptkbp:consists_of
|
nine tasks
|
|
gptkbp:designed_for
|
natural language understanding
|
|
gptkbp:evaluates
|
model performance
|
|
gptkbp:focuses_on
|
transfer learning
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
GLUE benchmark
|
|
gptkbp:influenced_by
|
gptkb:Super_GLUE
|
|
gptkbp:introduced
|
gptkb:Alex_Wang
|
|
gptkbp:is_compared_to
|
different models
|
|
gptkbp:is_maintained_by
|
AI researchers
|
|
gptkbp:is_often_used_in
|
gptkb:true
|
|
gptkbp:is_open_source
|
gptkb:true
|
|
gptkbp:is_tasked_with
|
gptkb:SST-2
gptkb:MNLI
QNLI
WNLI
RTE
QQP
MRPC
Co LA
|
|
gptkbp:is_used_in
|
NLP competitions
|
|
gptkbp:measures
|
generalization ability
|
|
gptkbp:performance
|
gptkb:Longformer
gptkb:Switch_Transformer
gptkb:BART
gptkb:social_reform
gptkb:GPT-3
gptkb:BERT
gptkb:T5
gptkb:Distil_BERT
gptkb:ELECTRA
gptkb:De_BERTa
gptkb:Ro_BERTa
gptkb:XLNet
gptkb:Vision_Transformers
gptkb:Pegasus
gptkb:Big_Bird
Hybrid models
ALBERT
transformer models
ERNIE
Ensemble models
Few-shot learning models
Meta-learning models
Multimodal models
Prompt-based models
Self-supervised models
Semi-supervised models
Supervised models
Unsupervised models
Zero-shot learning models
|
|
gptkbp:provides
|
leaderboard
|
|
gptkbp:provides_metrics
|
F1 score
accuracy
Matthew's correlation coefficient
|
|
gptkbp:published_in
|
gptkb:2018
|
|
gptkbp:used_by
|
gptkb:researchers
|
|
gptkbp:bfsParent
|
gptkb:Transformers
gptkb:Ford_Model_T
|
|
gptkbp:bfsLayer
|
4
|