Machine Translation on Portuguese-Arabic
17.66BLEU ScorePIVOTE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PIVOTEMerging Module=GPT-4o, Candidates=Direct & English Pivot2025.02 | 17.66 | 43.73 | 84.27 | |
| PIVOTEMerging Module=GPT-4, Candidates=Direct & English Pivot2025.02 | 17.02 | 43.02 | 84.82 | |
| PIVOTEMerging Module=GPT-4o, Candidates=top32025.02 | 16.92 | 42.93 | 84.52 | |
| PIVOTEMerging Module=GPT-4, Candidates=top32025.02 | 16.53 | 42.41 | 84.46 | |
| GPT-4otype=Standalone NMT System2025.02 | 16.28 | 42.4 | 83.82 | |
| GPT-4type=Standalone NMT System2025.02 | 15.11 | 41.39 | 83.99 | |
| MBRtype=Prior Ensemble Method2025.02 | 14.66 | 41.11 | 83.93 | |
| PIVOTEMerging Module=Llama-3, Candidates=top32025.02 | 14.27 | 38.25 | 81.8 | |
| NLLBtype=Standalone NMT System2025.02 | 13.5 | 40.9 | 84.24 | |
| PIVOTEMerging Module=Llama-3, Candidates=Direct & English Pivot2025.02 | 12.37 | 36.51 | 82.09 | |
| Llama-3type=Standalone NMT System2025.02 | 12.25 | 35.16 | 82.79 | |
| Baizetype=Standalone NMT System2025.02 | 8.5 | 27.28 | 79.18 | |
| Vicunatype=Standalone NMT System2025.02 | 8.4 | 27.38 | 79.18 | |
| EVAtype=Prior Ensemble Method2025.02 | 7.99 | 27 | 73.15 | |
| LLM-Blendertype=Prior Ensemble Method2025.02 | 0.94 | 2.69 | 46.49 |