Machine Translation on WMT En-Zh 22 (test)
86.8COMETWMT22 Winners
Evaluation results
| Method | Links | ||
|---|---|---|---|
| WMT22 Winners2024.06 | 86.8 | 54.3 | |
| TASTEBackbone=BLOOMZ-7b1-mt, Training Strategy=Tuning with Fixed Embedding Layer, Subtask Form=Text Classification2024.06 | 85.9 | 39.07 | |
| TASTEBackbone=BLOOMZ-7b1-mt, Training Strategy=Tuning with Fixed Embedding Layer, Subtask Form=Quality Estimation2024.06 | 85.81 | 39.31 | |
| MT-FixEmbBackbone=BLOOMZ-7b1-mt, Training Strategy=Tuning with Fixed Embedding Layer2024.06 | 85.2 | 36.68 | |
| TIMBackbone=BLOOMZ-7b1-mt2024.06 | 85.1 | 37.83 | |
| TASTEBackbone=BLOOMZ-7b1-mt, Training Strategy=Full-Parameter Tuning, Subtask Form=Quality Estimation2024.06 | 85.05 | 36.84 | |
| MT-FullBackbone=BLOOMZ-7b1-mt, Training Strategy=Full-Parameter Tuning2024.06 | 85.01 | 35.49 | |
| TASTEBackbone=BLOOMZ-7b1-mt, Training Strategy=Full-Parameter Tuning, Subtask Form=Text Classification2024.06 | 84.94 | 36.75 | |
| BaylingBackbone=LLaMA-2-7b2024.06 | 84.43 | 38.19 | |
| TASTEBackbone=LLaMA-2-7b, Training Strategy=Tuning with Fixed Embedding Layer, Subtask Form=Quality Estimation2024.06 | 84.3 | 34.94 | |
| TASTEBackbone=LLaMA-2-7b, Training Strategy=Tuning with Fixed Embedding Layer, Subtask Form=Text Classification2024.06 | 84.24 | 34.96 | |
| TASTEBackbone=LLaMA-2-7b, Training Strategy=Full-Parameter Tuning, Subtask Form=Text Classification2024.06 | 84 | 34.51 | |
| TASTEBackbone=LLaMA-2-7b, Training Strategy=Full-Parameter Tuning, Subtask Form=Quality Estimation2024.06 | 83.9 | 34.25 | |
| MT-FixEmbBackbone=LLaMA-2-7b, Training Strategy=Tuning with Fixed Embedding Layer2024.06 | 83.62 | 33.33 | |
| ParroTBackbone=BLOOMZ-7b1-mt2024.06 | 83.5 | 34.5 | |
| MT-FullBackbone=LLaMA-2-7b, Training Strategy=Full-Parameter Tuning2024.06 | 83.35 | 33.01 | |
| NLLB-3.3b2024.06 | 81.56 | 32.52 | |
| ParroTBackbone=LLaMA-2-7b2024.06 | 80.3 | 30.3 |