ROUGE-L

E2185208 UNEXPLORED

ROUGE-L is an automatic text evaluation metric that measures the quality of generated language by computing the longest common subsequence overlap between candidate and reference texts.

Try in SPARQL Jump to: Surface forms Referenced by

All labels observed (2)

Label	Occurrences
ROUGE	1
ROUGE-L canonical	1

Referenced by (2)

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

MSCOCO → evaluationMetric → ROUGE-L ⓘ

Flickr8k → hasEvaluationMetrics → ROUGE ⓘ

linked to: ROUGE-L