|
gptkbp:instanceOf
|
gptkb:dataset
|
|
gptkbp:assesses
|
accuracy
|
|
gptkbp:author
|
gptkb:Noah_A._Smith
gptkb:Yejin_Choi
gptkb:Chandra_Bhagavatula
gptkb:Swabha_Swayamdipta
Yichen Wang
|
|
gptkbp:contains
|
questions about everyday physical situations
|
|
gptkbp:createdBy
|
gptkb:Allen_Institute_for_AI
|
|
gptkbp:domain
|
commonsense reasoning
|
|
gptkbp:focus
|
physical commonsense reasoning
|
|
gptkbp:format
|
gptkb:JSON
|
|
gptkbp:fullName
|
gptkb:Physical_Interaction:_Question_Answering
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
PIQA
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
CC BY 4.0
|
|
gptkbp:memiliki_tugas
|
multiple-choice question answering
|
|
gptkbp:notablePublication
|
gptkb:PIQA:_Reasoning_about_Physical_Commonsense_in_Natural_Language
https://arxiv.org/abs/1911.11641
|
|
gptkbp:numberOfRooms
|
over 16,000
|
|
gptkbp:relatedTo
|
gptkb:Social_IQa
gptkb:commonsenseQA
|
|
gptkbp:releaseYear
|
2020
|
|
gptkbp:usedFor
|
benchmarking AI models
|
|
gptkbp:usedIn
|
natural language understanding research
|
|
gptkbp:website
|
https://allenai.org/data/piqa
|
|
gptkbp:bfsParent
|
gptkb:LLaMA_3
|
|
gptkbp:bfsLayer
|
7
|