BERT_large+ITPT

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Sentiment AnalysisonYelp Fine-grained classification
Error· 2019-05-14
28.62
best: 27.05 (XLNet)
SOTA
How to Fine-Tune BERT for Text Classification?arXiv:1905.05583
Sentiment AnalysisonYelp Binary classification
Error· 2019-05-14
1.81
best: 1.37 (XLNet)
SOTA
How to Fine-Tune BERT for Text Classification?arXiv:1905.05583
Sentiment AnalysisonIMDb
Accuracy· 2019-05-14
95.79
best: 96.68 (RoBERTa-large with LlamBERT)
How to Fine-Tune BERT for Text Classification?arXiv:1905.05583