Machine Translation on Human Evaluation set en-it 1.0 (test)
2.77Gender Agreement ScoreTranslate API
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Translate APIPrompting=Zero-shot, Evaluation Scale=0-3 scale2023.05 | 2.77 | 2.57 | |
| PaLMPrompting=Zero-shot, Evaluation Scale=0-3 scale2023.05 | 2.68 | 2.46 | |
| PaLM 2Prompting=Zero-shot, Evaluation Scale=0-3 scale2023.05 | 2.65 | 2.6 |