Skip to content

Machine Learning & Data Science Natural Language Processing ROUGE Score

github-actions[bot] edited this page Nov 22, 2025 · 1 revision

The ROUGE (Recall-Oriented Understudy for Gisting Evaluation) score is a metric used in natural language processing to evaluate the quality of automatically generated summaries or translations. It measures the similarity between the generated summary and a set of reference summaries.

There are a number of variations of this score.

ROUGE-N Score

The ROUGE-N Score is a variation on the ROUGE score which calculates the overlap between N-grams in the reference summary and the generated summary.

F1 Score

The Machine-Learning-&-Data-Science-Natural-Language-Processing-BLEU-Score and ROUGE-N scores can be combined to produce an F1 score:

Clone this wiki locally