Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BMELD

Benchmarks

Task NameDataset NameSOTA ResultTrend
Machine TranslationBMELD Ch=>En (test)
BLEU27.58
28
Machine TranslationBMELD (En=>Ch) (test)
BLEU32.87
28
Dialogue CoherenceBMELD (val)
Precision (1st)61.03
7
Machine Translation (Human Evaluation)BMELD En-Zh (test)
Coherence0.69
6
Showing 4 of 4 rows