Getting Started

Installation
Generate your synthetic document
OCR-NER Dataset Generation

Fabricating Document & Noise

Create a document
Degrade a document

Handling Noisy Text

Text alignment
Propagation of NER labels

API Documentation

genalog.degradation
genalog.generation
genalog.ocr
genalog.text

Powered by Jupyter Book

Search

Searching for multiple words only shows matches that contain all words.

By Jianjie Liu and Amit Gupte
© Copyright 2021.

Don't forget to check out our paper from Document Intelligence Workshop at KDD 2021!