按年被提到
20232023 · 4 次2026
大模型与语言模型›大模型文本、写作与版权·arXiv:2308.13418 · cs.LG

Nougat: Neural Optical Understanding for Academic Documents

Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2023-09-04 · 最近 2023-11-09
4不同的人
2活跃月份
3讨论串
131被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论dang · 2023-09

“We've changed to that first link from https://arxiv.org/abs/2308.13418. Thanks! Edit: recent and related: Nougat: Neural Optical Understanding for Academic Documents - https://news.ycombinator.com/item?id=37342215 - Aug 2023 (27 comments)”

Nougat: Neural Optical Understanding for Academic Documents原评论 ↗
评论mufasachan · 2023-11

“> Although the author OCR’ed the SAT questions and believes that they weren’t in the training data I agree that the author of the tweet fairly underestimates the potential portion of OCR'ed contents in OpenAI's training data. In late August, Nougat[1] is released by Meta, this is an OCR model. Its performance are wild and the model is open source. I har…”

Benchmarking GPT-4 Turbo – A Cautionary Tale原评论 ↗
被提交为 story · 2 次