ROUGE
- Recall-Oriented Understudy for Gisting Evaluation
- used to evaluate summarization / translation
- ROUGE metrics range between 0 and 1, with higher scores indicating higher similarity between the automatically produced summary and the reference
-
"rouge1": unigram (1-gram) based scoring
"rouge2": bigram (2-gram) based scoring"rougeL": Longest common subsequence based scoring."rougeLSum": splits text using"\n"