|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:applies_to
|
forms and invoices
|
|
gptkbp:architecture
|
gptkb:Transformers
|
|
gptkbp:based_on
|
gptkb:Transformers
|
|
gptkbp:can_be_used_in
|
NLP tasks
|
|
gptkbp:can_handle
|
noisy data
|
|
gptkbp:collaborated_with
|
academic institutions
|
|
gptkbp:developed_by
|
gptkb:Microsoft
key-value pairs
|
|
gptkbp:enhances
|
information extraction
|
|
gptkbp:has
|
multi-task learning capabilities
|
|
gptkbp:has_achieved
|
state-of-the-art results
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Layout LMv2
|
|
gptkbp:improves
|
OCR performance
|
|
gptkbp:input_output
|
structured information
text and layout information
Text and Layout
|
|
gptkbp:is_adopted_by
|
various industries
|
|
gptkbp:is_applied_in
|
data extraction tasks
|
|
gptkbp:is_available_on
|
gptkb:Hugging_Face_Model_Hub
|
|
gptkbp:is_compatible_with
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_designed_for
|
real-world applications
|
|
gptkbp:is_documented_in
|
research papers
technical reports
|
|
gptkbp:is_enhanced_by
|
transfer learning
|
|
gptkbp:is_evaluated_by
|
F1 score
accuracy and efficiency
benchmark datasets
|
|
gptkbp:is_featured_in
|
AI conferences
|
|
gptkbp:is_influenced_by
|
gptkb:Layout_LM
|
|
gptkbp:is_integrated_with
|
other AI tools
|
|
gptkbp:is_optimized_for
|
low-resource settings
|
|
gptkbp:is_part_of
|
AI research initiatives
AI development projects
NLP toolkit
Layout LM family
|
|
gptkbp:is_promoted_by
|
gptkb:Microsoft_Research
|
|
gptkbp:is_recognized_as
|
a leading model in document AI.
|
|
gptkbp:is_recognized_for
|
innovation in AI
|
|
gptkbp:is_supported_by
|
community contributions
open-source community
|
|
gptkbp:is_tasked_with
|
Document Understanding
|
|
gptkbp:is_tested_for
|
real-world datasets
|
|
gptkbp:is_trained_in
|
large-scale datasets
document images
Document Images
|
|
gptkbp:is_used_for
|
form understanding
|
|
gptkbp:is_used_in
|
research and industry
|
|
gptkbp:is_used_to
|
automate data entry
|
|
gptkbp:is_utilized_in
|
automated workflows
|
|
gptkbp:performance
|
other models
|
|
gptkbp:provides
|
contextual embeddings
|
|
gptkbp:release_date
|
gptkb:2021
|
|
gptkbp:successor
|
gptkb:Layout_LM
gptkb:Layout_LMv3
|
|
gptkbp:supports
|
fine-tuning
multi-modal inputs
|
|
gptkbp:tuning
|
specific tasks
|
|
gptkbp:used_for
|
document understanding
|
|
gptkbp:utilizes
|
visual features
|
|
gptkbp:bfsParent
|
gptkb:Super_GLUE_benchmark
|
|
gptkbp:bfsLayer
|
5
|