English

Nougat: Neural Optical Understanding for Academic Documents

Machine Learning 2023-08-28 v1 Computer Vision and Pattern Recognition

Abstract

Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents. The proposed approach offers a promising solution to enhance the accessibility of scientific knowledge in the digital age, by bridging the gap between human-readable documents and machine-readable text. We release the models and code to accelerate future work on scientific text recognition.

Keywords

Cite

@article{arxiv.2308.13418,
  title  = {Nougat: Neural Optical Understanding for Academic Documents},
  author = {Lukas Blecher and Guillem Cucurull and Thomas Scialom and Robert Stojnic},
  journal= {arXiv preprint arXiv:2308.13418},
  year   = {2023}
}

Comments

17 pages, 10 figures

R2 v1 2026-06-28T12:04:23.412Z