Text Analysis with Grobid

Description

This project uses Grobid, a machine learning software, to extract structured metadata and content from documents in PDF format. The extracted information includes a word cloud with the keywords of the abstracts of the all documents, a bar chart showing the number of figures and the URLs that appear in each PDF document.

Note: There are already 10 PDFs in the repository. If you want to process your own PDFs, please save them in the "papers" folder.