OpenCodePapers

relation-extraction-on-funsd

Relation 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
A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents90.81LayoutLMv3 large EM + BBO + RSF2024-04-16
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction✓ Link89.45GeoLayoutLM2023-04-21
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding✓ Link88.46RORE (GeoLayoutLM)2024-09-29
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking✓ Link80.35LayoutLMv3 large2022-04-18
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction✓ Link80.35LayoutLMv3 large2023-04-21
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction✓ Link79.20TPP (LayoutMask)2023-10-17
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents✓ Link77.01BROS2021-08-10
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding✓ Link70.57LayoutLMv2 large2020-12-29
LayoutLM: Pre-training of Text and Layout for Document Image Understanding✓ Link42.83LayoutLM2019-12-31
Check out how to contribute new results.