Concept
BLEU
BLEU (Bilingual Evaluation Understudy) is an automatic metric for scoring machine-translated text against one or more human reference translations. It exists because human evaluation is slow and expensive, and you need a number you can compute on every training checkpoint.
The rest of “BLEU” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→