awesome-document-understanding
github.com/tstanislawek/awesome-document-understanding ↗A curated list of resources for Document Understanding (DU) topic
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me conferences, workshops resources from awesome-document-understanding"
Installation instructions →What's inside
Blogs
Papers
- A Survey of Deep Learning Approaches for OCR and Document Understanding
- Business Document Information Extraction: Towards Practical Benchmarks
- Conversations with Documents. An Exploration of Document-Centered Assistance
- Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks
- DocILE Benchmark for Document Information Localization and Extraction
- Document AI: Benchmarks, Models and Applications
Resources
- borb
is a pure python library to read, write and manipulate PDF documents. It represents a PDF document as a JSON-like datastructure of nested lists, dictionaries and primitives (numbers, string, booleans, etc).
- Born digital pdf scanner
checking if pdf is born-digital
- Color Document Dataset
from the Intelligent Sensory Information Systems, University of Amsterdam
- deepdoctection
- Layout Parser
Layout Parser is a deep learning based tool for document image layout analysis tasks
- OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched or copy-pasted
Document Question Answering
Showing a sample of 95 resources. View the full list on GitHub →