Tense Reinflection on tense reinflection without auxiliary do (hierarchical)
94Partial AccuracyTree-GRU
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Tree-GRUSource=McCoy et al. (2020)2025.11 | 94 | — | |
| TfSource=Qin et al. (2025)2025.11 | 84 | — | |
| TfSource=Murty et al. (2023), Overtrained=false2025.11 | 83 | — | |
| TfSource=Ahuja et al. (2025), Training objective=language modeling objective2025.11 | 75 | — | |
| TfSource=Murty et al. (2023), Overtrained=true2025.11 | 46 | — | |
| RNN+Sup+R2025.11 | 33.1 | 0 | |
| Stack LSTM2025.11 | 24.3 | 0 | |
| Tf+Nd+Nd2025.11 | 10.1 | 8.6 | |
| TfGround-truth parse trees=true2025.11 | 8.6 | 7.9 | |
| LSTM+Nd+R2025.11 | 8.6 | 0 | |
| LSTM2025.11 | 6.7 | 0 | |
| Stack Attention Transformer2025.11 | 6.2 | 5.6 | |
| Tf+Sup+Sup2025.11 | 6.1 | 5.9 | |
| LSTM+Sup+R2025.11 | 5 | 0 | |
| ON-LSTMSource=McCoy et al. (2020)2025.11 | 5 | — | |
| Tf+Sup2025.11 | 4.8 | 3.6 | |
| LSTM+Sup2025.11 | 4.1 | 0 | |
| LSTMSource=McCoy et al. (2020)2025.11 | 4 | — | |
| RNN+Nd+R2025.11 | 3.7 | 0 | |
| Stack RNN2025.11 | 2.8 | 0 | |
| RNN+Sup2025.11 | 1.5 | 0 | |
| RNN2025.11 | 1.2 | 0 |