SOTAVerified

Key-value Pair Extraction

Extract key-value pairs from a form-like document.

A prediction is considered TP if the predicted key and value contents match the ground truths. Key-value pair F1-score is employed as the metric.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 12 papers

TitleStatusHype
OCR-free Document Understanding TransformerCode3
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document UnderstandingCode2
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path PredictionCode1
KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business DocumentsCode1
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair ExtractionCode1
LayoutLMv3: Pre-training for Document AI with Unified Text and Image MaskingCode0
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document UnderstandingCode0
GeoLayoutLM: Geometric Pre-training for Visual Information ExtractionCode0
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document UnderstandingCode0
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.