Statements (29)
Predicate | Object |
---|---|
gptkbp:instanceOf |
evaluation metric
|
gptkbp:alternativeMetric |
gptkb:ROUGE
gptkb:METEOR gptkb:chrF gptkb:COMET BERTScore |
gptkbp:calculationMethod |
geometric mean of n-gram precisions
brevity penalty applied |
gptkbp:commonIn |
natural language processing
machine translation research |
gptkbp:criticizedFor |
favoring short translations
not capturing semantic meaning |
gptkbp:fullName |
gptkb:Bilingual_Evaluation_Understudy_Score
|
gptkbp:higherIsBetter |
true
|
https://www.w3.org/2000/01/rdf-schema#label |
BLEU Score
|
gptkbp:input |
candidate translation
reference translation |
gptkbp:introduced |
gptkb:Kishore_Papineni
|
gptkbp:introducedIn |
2002
|
gptkbp:measures |
precision
n-gram overlap |
gptkbp:nGramsUsed |
typically 1-4
|
gptkbp:output |
score
|
gptkbp:publishedIn |
gptkb:ACL_2002
|
gptkbp:range |
0 to 1
|
gptkbp:usedFor |
machine translation evaluation
|
gptkbp:uses |
brevity penalty
|
gptkbp:bfsParent |
gptkb:Machine_Translation
|
gptkbp:bfsLayer |
6
|