Machine Translation on WMT22 En-Liv news
56.7COMETIBUT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| IBUTMode=Iterative Bilingual Understanding (IBUT)2024.10 | 56.7 | 44.2 | 4.7 | |
| ChatGPTMode=Reranking2024.10 | 55.5 | 42.7 | 2.9 | |
| ChatGPTMode=Multi-Agent Discussion (MAD)2024.10 | 55.5 | 42.5 | 3.1 | |
| ChatGPTMode=Iterative Refinement2024.10 | 55.5 | 42.7 | 3.3 | |
| ChatGPTMode=5-shot prompting2024.10 | 55.3 | 42.1 | 2.7 | |
| ChatGPTMode=Translation Error Analysis and Reduction (TEaR)2024.10 | 54.7 | 42.9 | 3.3 | |
| ChatGPTMode=Multi-Agent Prompt Selection (MAPS)2024.10 | 54.1 | 42 | 2.9 | |
| ChatGPTMode=Dual-Reflection2024.10 | 53.7 | 43 | 3.2 | |
| ChatGPTMode=Zero-shot2024.10 | 52.7 | 41.8 | 2.4 |