OpenCodePapers

key-information-extraction-on-cord

Document UnderstandingKey Information Extraction
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeF1ModelNameReleaseDate
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding✓ Link98.52RORE (GeoLayoutLM)2024-09-29
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction✓ Link97.97GeoLayoutLM2023-04-21
Unifying Vision, Text, and Layout for Universal Document Processing✓ Link97.58UDOP2022-12-05
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking✓ Link97.46LayoutLMv3 Large2022-04-18
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents✓ Link97.28BROS Large2021-08-10
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding✓ Link97.21ERNIE-Layout Large2022-10-12
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding97.19LayoutMask (large)2023-05-30
DocFormer: End-to-End Transformer for Document Understanding✓ Link96.99DocFormer Large (I+T+S)2021-06-22
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding96.99LayoutMask (base)2023-05-30
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction✓ Link96.92TPP (LayoutMask)2023-10-17
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding✓ Link96.07LILT2022-02-28
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding✓ Link96.01LayoutLMv2LARGE2020-12-29
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding✓ Link94.95LayoutLMv2BASE2020-12-29
Check out how to contribute new results. Then edit this file on GitLab or GitHub.