gptkbp:instanceOf
|
evaluation metric
|
gptkbp:commonIn
|
natural language processing
machine translation research
text summarization research
|
gptkbp:contrastsWith
|
reference summaries
system-generated summaries
|
gptkbp:fullName
|
gptkb:Recall-Oriented_Understudy_for_Gisting_Evaluation
|
https://www.w3.org/2000/01/rdf-schema#label
|
ROUGE
|
gptkbp:includesMetric
|
gptkb:ROUGE-L
gptkb:ROUGE-N
gptkb:ROUGE-S
gptkb:ROUGE-SU
gptkb:ROUGE-W
|
gptkbp:introduced
|
gptkb:Chin-Yew_Lin
|
gptkbp:introducedIn
|
2004
|
gptkbp:measures
|
precision
recall
word sequences
F1-score
overlap of n-grams
word pairs
|
gptkbp:officialWebsite
|
https://www.aclweb.org/anthology/W04-1013/
|
gptkbp:openSource
|
gptkb:Java
gptkb:Perl
gptkb:Python
|
gptkbp:publishedIn
|
gptkb:Proceedings_of_the_ACL_Workshop_on_Text_Summarization_Branches_Out
|
gptkbp:relatedTo
|
gptkb:METEOR
gptkb:BLEU
BERTScore
|
gptkbp:ROUGE-L
|
measures longest common subsequence
|
gptkbp:ROUGE-N
|
measures n-gram overlap
|
gptkbp:ROUGE-S
|
measures skip-bigram overlap
|
gptkbp:ROUGE-SU
|
measures skip-bigram plus unigram overlap
|
gptkbp:ROUGE-W
|
measures weighted longest common subsequence
|
gptkbp:usedFor
|
automatic summarization evaluation
machine translation evaluation
|
gptkbp:bfsParent
|
gptkb:Air_Canada_Rouge
|
gptkbp:bfsLayer
|
5
|