ROUGE
Recall-Oriented Understudy of Gisting Evaluation (ROUGE). It computes n-gram based recall for the candidate sentence with respect to the references. It is a popular metric for summarization evaluation, trying to answer how often the words (and/or n-grams) in the reference summaries appeared in the machine-generated summaries (compared to BLEU asking how often the words (and/or n-grams) in the machine-generated summaries appeared in the human-reference summaries).
Similar to BLEU, versions of ROUGE can be computed by varying the n-gram count. Two other versions of ROUGE are ROUGES and ROUGEL. ROUGES computes an F-measure with a recall bias using skip-bigrams, while ROUGEL uses the longest common subsequence between the candidate and ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access