🍐PEAR Paper, models, and data for 🍐PEAR, a reference-free pairwise MT evaluation model presented at ACL 2026. PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Paper • 2601.18006 • Published May 27 • 4 Prosho/pear Updated Jul 24 • 26 • 4 Prosho/pear-xl Updated Jul 24 • 15 • 4 Prosho/pear-data Viewer • Updated Jul 24 • 27.8M • 334 • 2
PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Paper • 2601.18006 • Published May 27 • 4
Translation Difficulty Estimators This collection hosts the two Translation Difficulty estimators studied in the EMNLP 2025 publication https://aclanthology.org/2025.findings-emnlp. Estimating Machine Translation Difficulty Paper • 2508.10175 • Published Aug 13, 2025 • 3 Prosho/sentinel-src-24 Translation • Updated Jul 12 • 18 • 2 Prosho/sentinel-src-25 Translation • Updated Jul 12 • 24 • 12
🍐PEAR Paper, models, and data for 🍐PEAR, a reference-free pairwise MT evaluation model presented at ACL 2026. PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Paper • 2601.18006 • Published May 27 • 4 Prosho/pear Updated Jul 24 • 26 • 4 Prosho/pear-xl Updated Jul 24 • 15 • 4 Prosho/pear-data Viewer • Updated Jul 24 • 27.8M • 334 • 2
PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation Paper • 2601.18006 • Published May 27 • 4
Translation Difficulty Estimators This collection hosts the two Translation Difficulty estimators studied in the EMNLP 2025 publication https://aclanthology.org/2025.findings-emnlp. Estimating Machine Translation Difficulty Paper • 2508.10175 • Published Aug 13, 2025 • 3 Prosho/sentinel-src-24 Translation • Updated Jul 12 • 18 • 2 Prosho/sentinel-src-25 Translation • Updated Jul 12 • 24 • 12
