|
gptkbp:instance_of
|
gptkb:language
|
|
gptkbp:applies_to
|
natural language processing
|
|
gptkbp:architecture
|
gptkb:Transformers
|
|
gptkbp:competes_with
|
gptkb:GPT-3
|
|
gptkbp:developed_by
|
gptkb:Microsoft_Research
|
|
gptkbp:first_released
|
gptkb:2020
|
|
gptkbp:has_achieved
|
state-of-the-art results
|
|
gptkbp:has_applications_in
|
machine translation
chatbots
information retrieval
text summarization
|
|
gptkbp:has_variants
|
gptkb:De_BERTa_v2
|
|
gptkbp:has_version
|
gptkb:De_BERTa-v2
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
De BERTa
|
|
gptkbp:improves
|
gptkb:BERT
|
|
gptkbp:is_applied_in
|
natural language processing
|
|
gptkbp:is_available_on
|
gptkb:Hugging_Face_Model_Hub
gptkb:Py_Torch_Hub
gptkb:Tensor_Flow_Hub
|
|
gptkbp:is_based_on
|
self-supervised learning
BERT architecture
|
|
gptkbp:is_documented_in
|
research papers
online tutorials
technical reports
Git Hub repositories
|
|
gptkbp:is_evaluated_by
|
gptkb:SQu_AD_benchmark
gptkb:TREC
gptkb:SQu_AD_v2.0
gptkb:GLUE_benchmark
gptkb:SQu_AD
gptkb:MNLI
gptkb:Super_GLUE_benchmark
gptkb:MNLI-matched
WNLI
RTE
QQP
STS-B
MRPC
Co LA
NLP leaderboards
MNLI-mismatched
|
|
gptkbp:is_influenced_by
|
gptkb:BERT
gptkb:Ro_BERTa
gptkb:XLNet
deep learning
attention mechanisms
transformer models
|
|
gptkbp:is_known_for
|
flexibility
high accuracy
scalability
robustness
adaptability
disentangled attention mechanism
|
|
gptkbp:is_optimized_for
|
gptkb:performance
large datasets
|
|
gptkbp:is_part_of
|
NLP research community
Microsoft AI ecosystem
transformer models family
NLP toolkit
|
|
gptkbp:is_related_to
|
gptkb:neural_networks
gptkb:machine_learning
deep learning
AI ethics
|
|
gptkbp:is_supported_by
|
community contributions
|
|
gptkbp:is_trained_in
|
large text corpora
masked language modeling
next sentence prediction
|
|
gptkbp:is_used_by
|
gptkb:developers
gptkb:researchers
data scientists
|
|
gptkbp:is_used_for
|
dialog systems
question answering
sentiment analysis
semantic analysis
text generation
text classification
language understanding
|
|
gptkbp:is_used_in
|
gptkb:academic_research
question answering
sentiment analysis
industry applications
text classification
|
|
gptkbp:performance
|
gptkb:GPT-3
gptkb:historical_memory
gptkb:Ro_BERTa
gptkb:XLNet
F1 score
accuracy
precision
ALBERT
|
|
gptkbp:supports
|
multiple languages
|
|
gptkbp:training
|
masked language modeling
next sentence prediction
|
|
gptkbp:uses
|
disentangled attention
|
|
gptkbp:bfsParent
|
gptkb:Attention_Is_All_You_Need
gptkb:GLUE_benchmark
gptkb:Super_GLUE_benchmark
|
|
gptkbp:bfsLayer
|
5
|