Statements (26)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
benchmark result
|
| gptkbp:achievedScore |
80.5
|
| gptkbp:assesses |
gptkb:BERT
|
| gptkbp:author |
gptkb:Jacob_Devlin
gptkb:Kenton_Lee gptkb:Ming-Wei_Chang gptkb:Kristina_Toutanova |
| gptkbp:date |
2018
|
| gptkbp:evaluatesOn |
gptkb:GLUE
|
| https://www.w3.org/2000/01/rdf-schema#label |
BERT on GLUE
|
| gptkbp:improves |
previous baselines
|
| gptkbp:memiliki_tugas |
gptkb:CoLA
gptkb:MNLI gptkb:MRPC gptkb:QNLI gptkb:STS-B gptkb:RTE gptkb:SST-2 gptkb:WNLI gptkb:QQP natural language understanding |
| gptkbp:pdf |
gptkb:BERT:_Pre-training_of_Deep_Bidirectional_Transformers_for_Language_Understanding
|
| gptkbp:reportsTo |
gptkb:Google_AI_Language
|
| gptkbp:scoreType |
average
|
| gptkbp:bfsParent |
gptkb:ALBERT
|
| gptkbp:bfsLayer |
6
|