|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:application
|
Question answering
Sentiment analysis
Text classification
Text summarization
Named entity recognition
|
|
gptkbp:architecture
|
gptkb:Transformers
|
|
gptkbp:attention_heads
|
gptkb:12
|
|
gptkbp:coat_of_arms
|
gptkb:12
|
|
gptkbp:developed_by
|
gptkb:Google
|
|
gptkbp:evaluates
|
Accuracy
Precision
Recall
F1 score
|
|
gptkbp:fine_tuning_task
|
Various NLP tasks
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
BERT-Base
|
|
gptkbp:input_output
|
Contextual embeddings
Tokenized text
|
|
gptkbp:is_a_framework_for
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
Apache License 2.0
|
|
gptkbp:max_input_length
|
512 tokens
|
|
gptkbp:orbital_period
|
110 million
|
|
gptkbp:output_dimensionality
|
768
|
|
gptkbp:pre_training_objective
|
Next sentence prediction
|
|
gptkbp:pre_training_task
|
Masked Language Model
|
|
gptkbp:provides_information_on
|
gptkb:Wikipedia
gptkb:Book_Corpus
|
|
gptkbp:related_model
|
gptkb:Distil_BERT
gptkb:Ro_BERTa
gptkb:XLNet
ALBERT
ERNIE
|
|
gptkbp:release_date
|
gptkb:2018
|
|
gptkbp:repository
|
gptkb:Git_Hub
|
|
gptkbp:successor
|
gptkb:BERT-Large
|
|
gptkbp:tokenization_method
|
Word Piece
|
|
gptkbp:use_case
|
Chatbots
Search engines
Information retrieval
Recommendation systems
Text mining
Language translation
Social media analysis
Spam detection
Dialogue systems
Content generation
Customer support automation
|
|
gptkbp:uses
|
Bidirectional context
|
|
gptkbp:bfsParent
|
gptkb:BERT
|
|
gptkbp:bfsLayer
|
5
|