|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:application
|
invoice processing
form processing
receipt processing
|
|
gptkbp:architecture
|
gptkb:Transformers
|
|
gptkbp:community_support
|
active
|
|
gptkbp:developed_by
|
gptkb:Microsoft
|
|
gptkbp:evaluates
|
F1 score
accuracy
|
|
gptkbp:feature
|
contextual embeddings
document layout analysis
fine-tuning capability
layout-aware representation
multi-modal input
sequence labeling
token classification
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Layout LM
|
|
gptkbp:influenced_by
|
gptkb:BERT
gptkb:Ro_BERTa
gptkb:XLNet
gptkb:Vi_T
|
|
gptkbp:input_output
|
structured data
text and layout information
Text and Layout
|
|
gptkbp:is_a_framework_for
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_cited_in
|
ar Xiv:1912.13318
|
|
gptkbp:is_tasked_with
|
Document Understanding
|
|
gptkbp:is_trained_in
|
large document datasets
Document Images
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
MIT License
|
|
gptkbp:performance
|
state-of-the-art
|
|
gptkbp:provides_information_on
|
gptkb:Doc_VQA
gptkb:FUNSD
gptkb:RVL-CDIP
gptkb:TREC-IS
publicly available datasets
SROIE
|
|
gptkbp:related_to
|
gptkb:Computer_Vision
Optical Character Recognition (OCR)
Natural Language Processing (NLP)
|
|
gptkbp:release_date
|
gptkb:2020
|
|
gptkbp:repository
|
gptkb:Git_Hub
|
|
gptkbp:successor
|
gptkb:Layout_LMv2
|
|
gptkbp:training
|
supervised learning
|
|
gptkbp:type
|
gptkb:AI_technology
|
|
gptkbp:used_for
|
document understanding
|
|
gptkbp:user_base
|
gptkb:developers
gptkb:researchers
business analysts
data scientists
AI practitioners
|
|
gptkbp:bfsParent
|
gptkb:Super_GLUE_benchmark
|
|
gptkbp:bfsLayer
|
5
|