SMART-MT-DNN

Reported on 1 benchmark across 1 task · 1 paper

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

Natural Language Processing1 result

Sentiment AnalysisonSST-2 Binary classification
Dev Accuracy· 2019-11-08
96.1
best: 96.9 (SMARTRoBERTa)
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization arXiv:1911.03437