Text Classification on Yelp Review 250 labels
42.68Top-1 ErrorSoftMatch/FreeMatch + SemiReward
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SoftMatch/FreeMatch + SemiRewardBackbone=Bert [Devlin et al., 2018], SemiReward=true2023.10 | 42.68 | 2.55 | |
| FlexMatch + SemiRewardBackbone=Bert [Devlin et al., 2018], SemiReward=true2023.10 | 42.76 | 2.55 | |
| Pseudo Label + SemiRewardBackbone=Bert [Devlin et al., 2018], SemiReward=true2023.10 | 42.99 | 2.55 | |
| FlexMatch# Labels=250, Backbone=Bert-Base2023.05 | 43.35 | — | |
| SoftMatch/FreeMatchBackbone=Bert [Devlin et al., 2018], SemiReward=false2023.10 | 43.91 | — | |
| SoftMatch# Labels=250, Backbone=Bert-Base2023.05 | 44.09 | — | |
| ILL# Labels=250, Backbone=Bert-Base2023.05 | 44.82 | — | |
| Dash# Labels=250, Backbone=Bert-Base2023.05 | 45.24 | — | |
| AdaMatch# Labels=250, Backbone=Bert-Base2023.05 | 45.4 | — | |
| CoMatch# Labels=250, Backbone=Bert-Base2023.05 | 45.4 | — | |
| Pseudo LabelBackbone=Bert [Devlin et al., 2018], SemiReward=false2023.10 | 46.09 | — | |
| FlexMatchBackbone=Bert [Devlin et al., 2018], SemiReward=false2023.10 | 46.09 | — | |
| SimMatch# Labels=250, Backbone=Bert-Base2023.05 | 46.12 | — | |
| FixMatch# Labels=250, Backbone=Bert-Base2023.05 | 46.52 | — | |
| FreeMatch# Labels=250, Backbone=Bert-Base2023.05 | 47.95 | — | |
| Mean-Teacher# Labels=250, Backbone=Bert-Base2023.05 | 50.6 | — | |
| VAT# Labels=250, Backbone=Bert-Base2023.05 | 52.97 | — | |
| MixMatch# Labels=250, Backbone=Bert-Base2023.05 | 53.98 | — | |
| Pseudo-Label# Labels=250, Backbone=Bert-Base2023.05 | 54.51 | — |