Machine Translation on WMT En-Es 13 (test)
35.4Tokenized BLEUAdapter
Evaluation results
| Method | Links | |
|---|---|---|
| AdapterTraining Strategy=pre-train & fine-tuned, Fine-tuning Status=fine-tuned2021.05 | 35.4 | |
| mRASP2Training Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 35 | |
| mRASP2Training Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 34.5 | |
| mRASPTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers, Fine-tuning Status=without fine-tune2021.05 | 34.3 | |
| mBARTTraining Strategy=pre-train & fine-tuned, Fine-tuning Status=fine-tuned2021.05 | 34 | |
| mRASPTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers, Fine-tuning Status=without fine-tune2021.05 | 34 | |
| AdapterTraining Strategy=pre-train & fine-tuned, Fine-tuning Status=fine-tuned2021.05 | 33.7 | |
| m-TransformerTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 33.7 | |
| Transformer-12Training Strategy=bilingual, Model Architecture (Layers)=12 layers2021.05 | 33.2 | |
| m-TransformerTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.05 | 32.8 |