ML Research Wiki / Benchmarks / Key Information Extraction / CORD

CORD

Key Information Extraction Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: F1

Top Performing Models

Rank Model Paper F1 Date Code
1 RORE (GeoLayoutLM) Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding 98.52 2024-09-29 📦 chongzhangFDU/ROOR
2 GeoLayoutLM GeoLayoutLM: Geometric Pre-training for Visual Information Extraction 97.97 2023-04-21 📦 alibabaresearch/advancedliteratemachinery
3 LayoutLMv3 Large LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking 97.46 2022-04-18 📦 huggingface/transformers 📦 microsoft/unilm 📦 pwc-1/Paper-9 📦 MindSpore-scientific-2/code-14
4 LayoutMask (large) LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding 97.19 2023-05-30 -
5 LayoutMask (base) LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding 96.99 2023-05-30 -
6 TPP (LayoutMask) Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction 96.92 2023-10-17 📦 chongzhangfdu/tpp 📦 WinterShiver/Token-Path-Prediction
7 LILT LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding 96.07 2022-02-28 📦 huggingface/transformers 📦 jpwang/lilt 📦 pwc-1/Paper-9 📦 MindSpore-scientific-2/code-14 📦 MS-P3/code3
8 LayoutLMv2LARGE LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding 96.01 2020-12-29 📦 huggingface/transformers 📦 PaddlePaddle/PaddleOCR 📦 microsoft/unilm
9 LayoutLMv2BASE LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding 94.95 2020-12-29 📦 huggingface/transformers 📦 PaddlePaddle/PaddleOCR 📦 microsoft/unilm

All Papers (9)

chongzhangFDU/ROOR
alibabaresearch/advancedliteratemachinery
huggingface/transformers microsoft/unilm
chongzhangfdu/tpp WinterShiver/Token-Path-Prediction
huggingface/transformers jpwang/lilt
huggingface/transformers PaddlePaddle/PaddleOCR
huggingface/transformers PaddlePaddle/PaddleOCR