Statements (34)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:text
|
| gptkbp:alternativeName |
BookCorpus dataset
|
| gptkbp:contains |
novels
stories |
| gptkbp:createdBy |
gptkb:Mike_Lewis
gptkb:Omer_Levy gptkb:Danqi_Chen gptkb:Jingfei_Du gptkb:Mandar_Joshi gptkb:Myle_Ott gptkb:Yinhan_Liu gptkb:Veselin_Stoyanov gptkb:Luke_Zettlemoyer gptkb:Naman_Goyal |
| gptkbp:domain |
fiction
|
| https://www.w3.org/2000/01/rdf-schema#label |
BookCorpus
|
| gptkbp:language |
English
|
| gptkbp:license |
not publicly available
|
| gptkbp:notableFor |
large-scale language model training
|
| gptkbp:numberOfBooks |
over 11,000
|
| gptkbp:publicationYear |
2015
|
| gptkbp:size |
800 million words
|
| gptkbp:source |
self-published books
|
| gptkbp:usedFor |
pretraining language models
BERT pretraining GPT pretraining |
| gptkbp:usedIn |
gptkb:BERT
gptkb:GPT gptkb:RoBERTa gptkb:XLNet |
| gptkbp:bfsParent |
gptkb:DistilBERT
gptkb:MobileBERT gptkb:RoBERTa |
| gptkbp:bfsLayer |
6
|