Text Classification on Amazon Review (test)
63.85Macro F1 ScorePrompt-based FT (hard)
Evaluation Results
| Method | Links | |
|---|---|---|
| Prompt-based FT (hard)Number of labeled samples=full, Backbone=RoBERTa-Large2023.05 | 63.85 | |
| Prompt-based FT (soft)Number of labeled samples=full, Backbone=RoBERTa-Large2023.05 | 63.32 | |
| Prompt-based FT (hard) + PCPNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 59.64 | |
| Prompt-based FT (soft) + PCPNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 59.16 | |
| Prompt-based FT (hard)Number of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 57.01 | |
| Prompt-based FT (soft)Number of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 55.03 | |
| FLEXMATCHNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 54.19 | |
| DASHNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 53.95 | |
| Prompt-based FT (hard) + PCPNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 53.44 | |
| ADAMATCHNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 53.05 | |
| Prompt-based FT (soft) + PCPNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 52.78 | |
| FIXMATCHNumber of labeled samples=200, Backbone=RoBERTa-Large2023.05 | 52.33 | |
| FLEXMATCHNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 45.48 | |
| ADAMATCHNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 44.66 | |
| Prompt-based FT (soft)Number of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 44.52 | |
| Prompt-based FT (hard)Number of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 44.34 | |
| FIXMATCHNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 44.26 | |
| DASHNumber of labeled samples=40, Backbone=RoBERTa-Large2023.05 | 44.09 |