SOTAVerified

Key Information Extraction

Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 74 papers

TitleStatusHype
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents—0
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair ExtractionCode1
Multimodal weighted graph representation for information extraction from visually rich documents.Code0
OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table RecognitionCode0
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency—0
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth EvaluationCode1
GenKIE: Robust Generative Multimodal Document Key Information ExtractionCode1
VKIE: The Application of Key Information Extraction on Video Text—0
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path PredictionCode1
PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction—0
Data Efficient Training of a U-Net Based Architecture for Structured Documents Localization—0
AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and ClassificationCode0
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts—0
End-to-End Document Classification and Key Information Extraction using Assignment Optimization—0
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding—0
DUBLIN -- Document Understanding By Language-Image Network—0
OCRBench: On the Hidden Mystery of OCR in Large Multimodal ModelsCode2
Information Redundancy and Biases in Public Document Information Extraction BenchmarksCode0
SIMARA: a database for key-value information extraction from full pages—0
Information Extraction from Documents: Question Answering vs Token Classification in real-world setups—0
GeoLayoutLM: Geometric Pre-training for Visual Information ExtractionCode0
PDFVQA: A New Dataset for Real-World VQA on PDF Documents—0
Form-NLU: Dataset for the Form Natural Language UnderstandingCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-LoopCode0
Show:102550
← PrevPage 2 of 3Next →
All datasetsCORDSROIEKleister NDASIMARA

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RORE (GeoLayoutLM)F198.52—Unverified
2GeoLayoutLMF197.97—Unverified
3LayoutLMv3 LargeF197.46—Unverified
4LayoutMask (large)F197.19—Unverified
5LayoutMask (base)F196.99—Unverified
6TPP (LayoutMask)F196.92—Unverified
7LILTF196.07—Unverified
8LayoutLMv2LARGEF196.01—Unverified
9LayoutLMv2BASEF194.95—Unverified
#ModelMetricClaimedVerifiedStatus
1LayoutLMv2LARGE (Excluding OCR mismatch)F197.81—Unverified
2RORE (GeoLayoutLM)F196.97—Unverified
3LayoutLMv2LARGEF196.61—Unverified
4LayoutLMv2BASEF196.25—Unverified
5ChatGPT 3.5 SpatialFormatAccuracy77—Unverified
#ModelMetricClaimedVerifiedStatus
1LayoutLMv2LARGEF185.2—Unverified
2LayoutLMv2BASEF183.3—Unverified
3LAMBERT (75M)F180.42—Unverified
#ModelMetricClaimedVerifiedStatus
1DANF1 (%)95.05—Unverified