MT-DNN-SMART_10%ofTrainingData

Reported on 2 benchmarks 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 Processing2 results

Natural Language InferenceonSciTail
Dev Accuracy· 2019-11-08
91.3
best: 96.1 (MT-DNN-SMART_100%ofTrainingData)
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization arXiv:1911.03437
Natural Language InferenceonSNLI
Dev Accuracy· 2019-11-08
88.7
best: 91.6 (MT-DNN-SMART_100%ofTrainingData)
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization arXiv:1911.03437