BLEU

E2185167 UNEXPLORED

BLEU is an automatic metric for evaluating the quality of machine-translated text by comparing it to one or more reference translations using n-gram overlap.

Try in SPARQL Jump to: Surface forms Referenced by

All labels observed (1)

Label	Occurrences
BLEU canonical	5

Referenced by (5)

Full triples — surface form annotated when it differs from this entity's canonical label.

WMT English-French dataset → evaluationMetric → BLEU ⓘ

Show and Tell → evaluationMetric → BLEU ⓘ

MSCOCO → evaluationMetric → BLEU ⓘ

Flickr8k → hasEvaluationMetrics → BLEU ⓘ

CIDEr → relatedMetric → BLEU ⓘ