Text Classification on HyperPartisan
95.16F1 ScoreRoBERTa-large
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RoBERTa-largeParam=355M, Data=160G, FLOPS=4.36E212023.05 | 95.16 | — | |
| TLM(Medium)Param=109M, Data=1.21G, FLOPS=8.30E182023.05 | 94.05 | — | |
| TLM(Large)Param=109M, Data=3.64G, FLOPS=2.33E192023.05 | 93.92 | — | |
| TLM(Small)Param=109M, Data=0.91G, FLOPS=2.74E182023.05 | 93.53 | — | |
| ISS(Small-scale)Param=109M, Data=0.18G, FLOPS=1.82E182023.05 | 93.53 | — | |
| RoBERTa-BaseParam=125M, Data=160G, FLOPS=1.54E212023.05 | 93.53 | — | |
| TLM(Medium-20%)Param=109M, Data=0.18G, FLOPS=4.15E182023.05 | 93.53 | — | |
| ISS(Medium-scale)Param=109M, Data=0.18G, FLOPS=4.15E182023.05 | 93.53 | — | |
| ISS(Large-scale)Param=109M, Data=0.72G, FLOPS=8.30E182023.05 | 93.53 | — | |
| TLM(Small-20%)Param=109M, Data=0.18G, FLOPS=1.82E182023.05 | 93.11 | — | |
| TLM(Large-20%)Param=109M, Data=0.72G, FLOPS=8.30E182023.05 | 92.72 | — | |
| Bert-BaseParam=109M, Data=16G, FLOPS=2.79E192023.05 | 91.93 | — | |
| Bert LargeParam=355M, Data=16G, FLOPS=9.07E192023.05 | 91.62 | — | |
| FE-MLM + SpanMasking Unit=Span, Masking Strategy=Fully-Explored MLM, Domain Pre-training=News2020.10 | 0.9322 | — | |
| FE-MLM + SubwordMasking Unit=Subword, Masking Strategy=Fully-Explored MLM, Domain Pre-training=News2020.10 | 0.9235 | — | |
| MLM + SpanMasking Unit=Span, Masking Strategy=Standard MLM, Domain Pre-training=News2020.10 | 0.9172 | — | |
| MLM + SubwordMasking Unit=Subword, Masking Strategy=Standard MLM, Domain Pre-training=News2020.10 | 0.91 | — | |
| DAPTDomain Pre-training=News, Masking Strategy=Standard MLM2020.10 | 0.882 | — | |
| RoBERTaDomain Pre-training=None, Masking Strategy=Standard MLM2020.10 | 0.866 | — | |
| SoTA2020.07 | — | 90.6 |