Project Aim: To rewrite lukas-blecher's Nougat (Meta Research's NLP project) from scratch from personal learning purposes. Also aiming to productionalize this tool to an open-source free-to-use platform to practice MLOps skills.
Goal: This tool accepts uneditable academic PDFs and converts them to editable LaTeX markdown files. We use Optical Character Recognition models (Swin Transformer) paired with Semantic Learning models (mBART Transformer Decoder) to do this.
Citation for Nougat project:
@misc{blecher2023nougat,
title={Nougat: Neural Optical Understanding for Academic Documents},
author={Lukas Blecher and Guillem Cucurull and Thomas Scialom and Robert Stojnic},
year={2023},
eprint={2308.13418},
archivePrefix={arXiv},
primaryClass={cs.LG}
}