Sentiment Classification on Amazon (OOD)
90.62AccuracyStatic + 950 auto
Evaluation results
| Method | Links | |
|---|---|---|
| Static + 950 autoTraining set size=1000, Backbone=RoBERTa-base2022.03 | 90.62 | |
| DynamicTraining set size=800 total, Backbone=RoBERTa2022.03 | 90.51 | |
| Manual CADTraining set size=3,414 gold, Backbone=RoBERTa2022.03 | 90.48 | |
| Automatics CADTraining set size=3,414 total, Backbone=RoBERTa2022.03 | 90.46 | |
| FullTraining set size=1707, Backbone=RoBERTa-base2022.03 | 90.29 | |
| Dynamic-MRTraining set size=800 total, Backbone=RoBERTa2022.03 | 90.22 | |
| Static + 750 autoTraining set size=800, Backbone=RoBERTa-base2022.03 | 90.18 | |
| Static + 1150 autoTraining set size=1200, Backbone=RoBERTa-base2022.03 | 90.16 | |
| Dynamic-FRTraining set size=800 total, Backbone=RoBERTa2022.03 | 90.12 | |
| Static + 350 autoTraining set size=400, Backbone=RoBERTa-base2022.03 | 90.09 | |
| Static + 350 autoTraining set size=400 total, Backbone=RoBERTa2022.03 | 90.09 | |
| Static + 150 autoTraining set size=200, Backbone=RoBERTa-base2022.03 | 89.81 | |
| ALTraining set size=100 gold, Backbone=RoBERTa2022.03 | 89.8 | |
| RRTraining set size=400, Backbone=RoBERTa-base2022.03 | 89.73 | |
| Static + 550 autoTraining set size=600, Backbone=RoBERTa-base2022.03 | 89.67 | |
| StaticTraining set size=50, Backbone=RoBERTa-base2022.03 | 89.63 | |
| StaticTraining set size=50 gold, Backbone=RoBERTa2022.03 | 89.63 | |
| DPTraining set size=400, Backbone=RoBERTa-base2022.03 | 89.15 |