Python PDF parser for scientific publications: content and figures

A set of tools to allow PDF to XML conversion, utilising Apache Beam and other tools. The aim of this project is to bring multiple tools together to generate a full XML document.

Streamlit PDF viewer

A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines.

Viewer for the structure extracted by Grobid on PDF documents

Grobid module for superconductor material and properties extraction

Python library for serializing GROBID TEI XML to dataclass

A tool for the bibliographic analysis of the NIME proceedings archive

Staging-area for automatically collected experimental data for the SuperCon database with a curation interface with enhanced-document viewer and curation-ready interface

Final project as Computer Science Student at Telkom University || Stay tune guys at https://skripsi.fanzru.dev.

ENLIT is a tool that supports scholars in exploring new literature

Grobid couldn't thug it out... This is a Go sidecar app that spins up alongside a Grobid container and limits the flow of requests to it, as Grobid is quite fragile.

A Go (golang) client for GROBID.

PDF → GROBID = bibliographic metadata → BibSonomy

Author Entity disambiguation for the new ACL Anthology

A set of tools to allow PDF to XML conversion, utilising Apache Beam and other tools. The aim of this project is to bring multiple tools together to generate a full XML document. It is now mainly used for evaluation purpose of external tools.

Automatic research paper parser and guide to extract all the data from PDF file into JSON format

Information extraction from unstructured text to build a knowledge graph using techniques from traditional NLP to pre-trained transformers and LLMs for NER and Linking, and Relation Extraction.

A NLP based data extractor. This model works to extract mentioned data setfrom research papers.