Text Classification on MR, CR, MPQA, SUBJ, TREC (Noise Rate 0%)
84.2MR AccuracyREGSL
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| REGSLArchitecture=three-layer feed forward network, Pre-trained=SST, Noise Rate=0%, Number of random seeds=52021.11 | 84.2 | 84.35 | 87.95 | 93.5 | 83.73 | |
| l2-PGMArchitecture=three-layer feed forward network, Pre-trained=SST, Noise Rate=0%, Number of random seeds=52021.11 | 84.16 | 83.87 | 87.77 | 93.16 | 84.48 | |
| Fine-tuningArchitecture=three-layer feed forward network, Pre-trained=SST, Noise Rate=0%, Number of random seeds=52021.11 | 83.37 | 83.29 | 87.56 | 93.14 | 83.28 |