Statements (20)
Predicate | Object |
---|---|
gptkbp:instanceOf |
benchmark platform
|
gptkbp:developedBy |
gptkb:Facebook_AI_Research
|
gptkbp:enables |
adversarial data collection
human-in-the-loop evaluation |
gptkbp:focusesOn |
dynamic benchmarking
|
https://www.w3.org/2000/01/rdf-schema#label |
Dynabench
|
gptkbp:launched |
2020
|
gptkbp:memiliki_tugas |
question answering
sentiment analysis hate speech detection natural language inference |
gptkbp:openSource |
true
|
gptkbp:relatedTo |
gptkb:machine_learning
benchmarking AI model robustness |
gptkbp:supports |
NLP tasks
|
gptkbp:usedFor |
evaluating AI models
|
gptkbp:website |
https://dynabench.org/
|
gptkbp:bfsParent |
gptkb:Meta_AI
|
gptkbp:bfsLayer |
5
|