|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:attentionMechanism
|
self-attention
|
|
gptkbp:author
|
gptkb:Jacob_Devlin
gptkb:Kenton_Lee
gptkb:Ming-Wei_Chang
gptkb:Kristina_Toutanova
|
|
gptkbp:citation
|
over 50,000 (as of 2023)
|
|
gptkbp:developedBy
|
gptkb:Google
|
|
gptkbp:format
|
WordPiece tokens
|
|
gptkbp:fullName
|
gptkb:Bidirectional_Encoder_Representations_from_Transformers
|
|
gptkbp:github
|
https://github.com/google-research/bert
|
|
gptkbp:hasVariant
|
gptkb:BERT_Base
gptkb:BERT_Large
gptkb:Chinese_BERT
gptkb:Multilingual_BERT
|
|
gptkbp:headOfState
|
12 (BERT Base)
16 (BERT Large)
|
|
gptkbp:hiddenSize
|
1024 (BERT Large)
768 (BERT Base)
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
BERT
|
|
gptkbp:influenced
|
gptkb:ERNIE
gptkb:ALBERT
gptkb:DistilBERT
gptkb:RoBERTa
gptkb:XLNet
|
|
gptkbp:introducedIn
|
2018
|
|
gptkbp:language
|
English
|
|
gptkbp:layer
|
12 (BERT Base)
24 (BERT Large)
|
|
gptkbp:license
|
Apache 2.0
|
|
gptkbp:maxSequenceLength
|
512
|
|
gptkbp:notableFor
|
improving state-of-the-art on NLP tasks
|
|
gptkbp:notablePublication
|
gptkb:BERT:_Pre-training_of_Deep_Bidirectional_Transformers_for_Language_Understanding
|
|
gptkbp:openSource
|
true
|
|
gptkbp:parameter
|
110 million (BERT Base)
340 million (BERT Large)
|
|
gptkbp:pretrainingTask
|
masked language modeling
next sentence prediction
|
|
gptkbp:programmingLanguage
|
gptkb:Python
|
|
gptkbp:publishedIn
|
gptkb:NAACL_2019
|
|
gptkbp:relatedTo
|
gptkb:NLP
deep learning
transformers
|
|
gptkbp:supports
|
transfer learning
fine-tuning
|
|
gptkbp:tokenizer
|
gptkb:WordPiece
|
|
gptkbp:trainer
|
gptkb:English_Wikipedia
gptkb:BooksCorpus
|
|
gptkbp:usedFor
|
natural language processing
question answering
sentiment analysis
text classification
named entity recognition
|
|
gptkbp:bfsParent
|
gptkb:transformation
gptkb:convolutional_neural_network
gptkb:GPT-3
gptkb:Zhenzhong_Lan
gptkb:ERNIE
gptkb:Google_AI
gptkb:LaMDA
gptkb:Large_Language_Models
|
|
gptkbp:bfsLayer
|
5
|