Bilingual Evaluation Understudy
GPTKB entity
Statements (24)
Predicate | Object |
---|---|
gptkbp:instanceOf |
machine translation evaluation metric
|
gptkbp:abbreviation |
gptkb:BLEU
|
gptkbp:basedOn |
n-gram precision
|
gptkbp:field |
natural language processing
computational linguistics |
https://www.w3.org/2000/01/rdf-schema#label |
Bilingual Evaluation Understudy
|
gptkbp:influenced |
gptkb:ROUGE
gptkb:METEOR gptkb:TER ChrF |
gptkbp:introduced |
gptkb:Kishore_Papineni
|
gptkbp:introducedIn |
2002
|
gptkbp:language |
English
|
gptkbp:limitation |
does not account for synonyms
sensitive to exact word matches |
gptkbp:measures |
similarity between machine translation and reference translation
|
gptkbp:penalty |
short translations
|
gptkbp:publishedIn |
gptkb:ACL_2002
|
gptkbp:type |
automatic evaluation metric
|
gptkbp:usedFor |
evaluating machine translation quality
|
gptkbp:uses |
brevity penalty
|
gptkbp:bfsParent |
gptkb:BLEU_metric
gptkb:BLEU |
gptkbp:bfsLayer |
7
|