|
gptkbp:instance_of
|
gptkb:Performance_Monitoring
|
|
gptkbp:aims_to
|
advance AI
|
|
gptkbp:available_at
|
super.glue.ai
|
|
gptkbp:consists_of
|
multiple tasks
|
|
gptkbp:developed_by
|
gptkb:Allen_Institute_for_AI
language models
|
|
gptkbp:encourages
|
robustness in models
|
|
gptkbp:evaluates
|
natural language understanding
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Super GLUE benchmark
|
|
gptkbp:improves
|
gptkb:GLUE_benchmark
|
|
gptkbp:is_based_on
|
gptkb:GLUE
|
|
gptkbp:is_cited_in
|
academic papers
|
|
gptkbp:is_considered_as
|
challenging benchmark
|
|
gptkbp:is_evaluated_by
|
F1 score
accuracy
exact match
|
|
gptkbp:is_influential_in
|
NLP field
|
|
gptkbp:is_part_of
|
gptkb:AI_technology
|
|
gptkbp:is_popular_among
|
NLP practitioners
|
|
gptkbp:is_related_to
|
gptkb:machine_learning
deep learning
|
|
gptkbp:is_tasked_with
|
gptkb:AX-g
gptkb:Re_Co_RD
gptkb:CB
gptkb:COPA
AX-b
Bool Q
Multi RC
Wi C
|
|
gptkbp:is_tested_for
|
transformer models
|
|
gptkbp:is_used_for
|
model comparison
|
|
gptkbp:measures
|
model performance
|
|
gptkbp:performance
|
gptkb:Code_BERT
gptkb:Fin_BERT
gptkb:Graph-BERT
gptkb:Grok_Net
gptkb:Layout_LM
gptkb:Legal_BERT
gptkb:Sci_BERT
gptkb:Switch_Transformer
gptkb:Turing-NLG
gptkb:Turing-NLG_17_B
gptkb:Uni_LM
gptkb:m_T5
gptkb:BERTweet
gptkb:BART
gptkb:GPT-3
gptkb:BERT
gptkb:T5
gptkb:CTRL
gptkb:Distil_BERT
gptkb:ELECTRA
gptkb:Bio_BERT
gptkb:Clinical_BERT
gptkb:De_BERTa
gptkb:Ro_BERTa
gptkb:XLNet
gptkb:Pegasus
gptkb:GShard
gptkb:Layout_LMv2
gptkb:Layout_LMv3
ALBERT
MASS
ERNIE
|
|
gptkbp:provides
|
leaderboard
|
|
gptkbp:released_in
|
gptkb:2019
|
|
gptkbp:supports
|
transfer learning
|
|
gptkbp:used_by
|
gptkb:researchers
|
|
gptkbp:bfsParent
|
gptkb:Transformers
|
|
gptkbp:bfsLayer
|
4
|