About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Lukas Blecher
- sl:arxiv_num : 2308.13418
- sl:arxiv_published : 2023-08-25T15:03:36Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : Nougat: Neural Optical Understanding for Academic Documents@en
- sl:arxiv_updated : 2023-08-25T15:03:36Z
- sl:bookmarkOf : https://arxiv.org/abs/2308.13418
- sl:creationDate : 2023-09-17
- sl:creationTime : 2023-09-17T18:36:48Z
Documents with similar tags (experimental)