Sentiment Classification on Laptop14
85.11AccuracyBOOSTAUG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BOOSTAUGModel=FastLCF, Base Augmentation=EDA2022.10 | 85.11 | 82.18 | |
| BOOSTAUGModel=DeBERTa, Base Augmentation=EDA2022.10 | 84.56 | 81.77 | |
| BackTranslationAugModel=DeBERTa2022.10 | 84.17 | 81.15 | |
| VanillaModel=DeBERTa2022.10 | 83.31 | 80.02 | |
| VanillaModel=FastLCF2022.10 | 83.23 | 79.68 | |
| BackTranslationAugModel=FastLCF2022.10 | 82.76 | 79.82 | |
| EDAModel=FastLCF2022.10 | 81.97 | 79.57 | |
| SplitAugModel=FastLCF2022.10 | 81.82 | 78.46 | |
| EDAModel=DeBERTa2022.10 | 80.96 | 78.65 | |
| SpellingAugModel=DeBERTa2022.10 | 80.17 | 76.01 | |
| BOOSTAUGModel=BERT, Base Augmentation=EDA2022.10 | 80.1 | 76.48 | |
| BackTranslationAugModel=BERT2022.10 | 79.94 | 76.19 | |
| SpellingAugModel=FastLCF2022.10 | 79.62 | 74.81 | |
| VanillaModel=BERT2022.10 | 79.47 | 75.7 | |
| SplitAugModel=DeBERTa2022.10 | 79.15 | 75.72 | |
| ContextualWordEmbsAugModel=FastLCF2022.10 | 79.08 | 74.61 | |
| EDAModel=BERT2022.10 | 78.37 | 74.23 | |
| ContextualWordEmbsAugModel=DeBERTa2022.10 | 76.88 | 71.98 | |
| ContextualWordEmbsAugModel=BERT2022.10 | 75.63 | 70.79 | |
| SplitAugModel=BERT2022.10 | 75.47 | 70.56 | |
| SpellingAugModel=BERT2022.10 | 73.59 | 69.11 | |
| BOOSTAUGModel=LSTM, Base Augmentation=EDA2022.10 | 73.2 | 67.46 | |
| VanillaModel=LSTM2022.10 | 71.32 | 65.45 | |
| EDAModel=LSTM2022.10 | 68.65 | 62.09 | |
| BackTranslationAugModel=LSTM2022.10 | 68.5 | 62.22 | |
| ContextualWordEmbsAugModel=LSTM2022.10 | 67.4 | 61.57 | |
| SpellingAugModel=LSTM2022.10 | 67.24 | 60.3 | |
| SplitAugModel=LSTM2022.10 | 62.98 | 56.53 |