Skip to content
Chris Sweet edited this page Feb 23, 2025 · 2 revisions

Welcome to the FUNSD wiki!

About

This repository contains the FUNSD dataset along with the Azure Document Intelligence OCR output.

It also includes Jupyter Notebooks and Python code for analysis.

Experiments

Our current experiments on utilizing the OCR output layout extraction for semantic chunking can be found on the Semantic Chunking with Layout Extraction page.

Clone this wiki locally