Machine Translation on WMT Supervised Representative Directions (test)
33.01BLEU (Tokenized Average)mRASP2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| mRASP2Training Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 33.01 | 1.98 | |
| mRASPTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers, Fine-tuning Status=without fine-tune2021.05 | 32.33 | 1.3 | |
| m-TransformerTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 31.03 | — |