Statements (58)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
benchmark
|
| gptkbp:features |
multiple language pairs
|
| gptkbp:firstIntroduced |
2006
|
| gptkbp:hasAnnualEvents |
WMT_conference
|
| gptkbp:hasCollaboratedWith |
international community
other benchmarks evaluation campaigns |
| gptkbp:hasImpactOn |
translation quality
|
| https://www.w3.org/2000/01/rdf-schema#label |
WMT benchmark
|
| gptkbp:includes |
translation tasks
|
| gptkbp:isAssociatedWith |
open-source tools
|
| gptkbp:isCitedIn |
academic papers
|
| gptkbp:isDiscussedIn |
workshops
webinars seminars |
| gptkbp:isDocumentedIn |
conference proceedings
research articles technical reports |
| gptkbp:isEvaluatedBy |
METEOR
TER chrF BLEU_score |
| gptkbp:isInfluencedBy |
artificial intelligence
machine learning |
| gptkbp:isOrganizedBy |
gptkb:ACL
|
| gptkbp:isPartOf |
NLP_evaluation_frameworks
|
| gptkbp:isPromotedBy |
universities
industry leaders research institutions |
| gptkbp:isRecognizedBy |
government organizations
industry experts academic community |
| gptkbp:isSupportedBy |
grants
funding agencies sponsorships various datasets |
| gptkbp:isUpdatedBy |
evaluation tasks
|
| gptkbp:isUsedBy |
developers
researchers |
| gptkbp:isUsedIn |
NLP_community
|
| gptkbp:isUtilizedFor |
emerging technologies
novel algorithms new translation models |
| gptkbp:isUtilizedIn |
challenges
competitions hackathons |
| gptkbp:officialLanguage |
gptkb:Spanish
Chinese English French German |
| gptkbp:originatedIn |
workshop on statistical machine translation
|
| gptkbp:provides |
standardized evaluation metrics
test sets training sets |
| gptkbp:relatedTo |
machine translation
automatic translation systems |
| gptkbp:usedFor |
evaluating translation systems
|