pdf-benchmark
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents
- 33
- Python
- 4 y ago
gipplab
Scientific Information Analytics Group of Prof. Bela Gipp at the University of Göttingen
Built from gipplab's public GitHub profile, Germany. Not on Take My Repo yet, so there are no posts or updates here.
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents
This project provides various tools for processing content MathML with Java.
>>PhysWikiQuiz<< - a Physics Question Generation and Interrogation System
Prototype of an external plagiarism detection system that combines the analysis of citations and text in academic documents to improve the identification of disguised forms of academic plagiarism
Discovering Mathematical Objects of Interest - A Study of Mathematical Notations
CiteAssist generates preprints, suggests related papers, and adds BibTeX annotation to the PDF
This is the official code for the paper: ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents
>>AnnoMathTeX<< - a LaTeX formula annotation facilitation and recommendation tool for STEM documents
Set of tools we used to create, cultivate and process datasets for our math2vec project.
This repository contains the resources used for SIGIR'2024 paper "Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange"
Methods for Formula Concept Discovery (FCD) and Formula Concept Recognition (FCR)
The chemical formula extraction parses PDF files and extracts all checmical entities from these files.
ImagePlag is an adaptive, scalable, and extensible image-based plagiarism detection system suitable for analyzing a wide range of image similarities.
Project template for the Python course Winter 2023 at the University of Göttingen