ROUGE (Recall-Oriented Understudy for Gisting Evaluation), introduced by Chin-Yew Lin in 2004, is a family of summarization metrics whose variants — ROUGE-1, ROUGE-2, ROUGE-L — measure recall-oriented n-gram or longest-common-subsequence overlap. It's the summarization counterpart of BLEU and was the standard reference for years. The same critiques apply — surface lexical overlap misses meaning — but it's still reported as a quick sanity check on basic summarization ability, with modern evaluations supplemented by LLM-as-Judge.
MEVZU N°124ISTANBULYEAR I — VOL. III
Glossary · Intermediate · 2004
ROUGE
A classic summarization metric based on n-gram and sequence overlap.
- EN — English term
- ROUGE
- TR — Turkish term
- ROUGE