Meta’s latest AI model makes scientific PDFs machine-readable
https://arxiv.org/abs/2308.13418
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.
Well, this is interesting.
Imagine being able to give this prompt to your AI-based research assistant: “Retrieve all articles from these 5 journals [add RSS feeds here], published in the last 5 years. Summarise those articles which meet these criteria [citation metrics, authors, etc.) and present the key lines of inquiry. Identify gaps in the research and suggest a range of research questions that might be useful to explore”.
I can imagine a wide range of similar questions you could consider.