BART-RF-T1 hybrid

Reported on 2 benchmarks across 2 tasks · 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 Processing1 result

Text ClassificationonWeeBit (Readability Assessment)
Accuracy (5-fold)· 2021-09-25
0.905
best: 0.927 (BERT-FP-LBL)
SOTA
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features arXiv:2109.12258

Methodology1 result

ClassificationonWeeBit (Readability Assessment)
Accuracy (5-fold)· 2021-09-25
0.905
best: 0.927 (BERT-FP-LBL)
SOTA
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features arXiv:2109.12258