Sentiment Classification on SemEval 2017 (OOD)
82.39AccuracyDynamic-FR
Evaluation results
| Method | Links | |
|---|---|---|
| Dynamic-FRTraining set size=800 total, Backbone=RoBERTa2022.03 | 82.39 | |
| Static + 950 autoTraining set size=1000, Backbone=RoBERTa-base2022.03 | 80.9 | |
| Static + 550 autoTraining set size=600, Backbone=RoBERTa-base2022.03 | 80.69 | |
| Static + 750 autoTraining set size=800, Backbone=RoBERTa-base2022.03 | 80.55 | |
| Static + 350 autoTraining set size=400, Backbone=RoBERTa-base2022.03 | 80.54 | |
| Static + 350 autoTraining set size=400 total, Backbone=RoBERTa2022.03 | 80.54 | |
| DynamicTraining set size=800 total, Backbone=RoBERTa2022.03 | 80.32 | |
| Automatics CADTraining set size=3,414 total, Backbone=RoBERTa2022.03 | 79.39 | |
| Static + 1150 autoTraining set size=1200, Backbone=RoBERTa-base2022.03 | 79.31 | |
| RRTraining set size=400, Backbone=RoBERTa-base2022.03 | 79.2 | |
| Dynamic-MRTraining set size=800 total, Backbone=RoBERTa2022.03 | 79.04 | |
| Static + 150 autoTraining set size=200, Backbone=RoBERTa-base2022.03 | 78.88 | |
| ALTraining set size=100 gold, Backbone=RoBERTa2022.03 | 78.61 | |
| StaticTraining set size=50, Backbone=RoBERTa-base2022.03 | 77.28 | |
| StaticTraining set size=50 gold, Backbone=RoBERTa2022.03 | 77.28 | |
| DPTraining set size=400, Backbone=RoBERTa-base2022.03 | 74.36 | |
| FullTraining set size=1707, Backbone=RoBERTa-base2022.03 | 71.17 | |
| Manual CADTraining set size=3,414 gold, Backbone=RoBERTa2022.03 | 69.98 |