Models and paper for COMET-poly: Machine Translation Metric Grounded in Other Candidates
Vilém Zouhar
zouharvi
AI & ML interests
MT/NLG metrics, human evaluation, uncertainty
Recent Activity
updated a model 1 day ago
zouharvi/COMET-poly-cand1-wmt25 updated a model 1 day ago
zouharvi/COMET-poly-base-wmt25 updated a model 1 day ago
zouharvi/COMET-poly-ic3-wmt25Organizations
Models and paper for COMET-poly: Machine Translation Metric Grounded in Other Candidates
Phonetic Word Embeddings
Models introduced in the paper Early-Exit and Instant Confidence Translation Quality Estimation https://github.com/zouharvi/COMET-early-exit
COMET-like models for MT evaluation that predict some scores given only the source segment. https://github.com/zouharvi/subset2evaluate