#information-extraction Repositories
Discover 42 active open source GitHub repositories tagged with #information-extraction, accumulating 83,368 total stars (averaging 1,984 stars per project). Leading this topic is PaddlePaddle/PaddleNLP with 13,000 stars.
42 repositories total
A tutorial and implementation of a disease-centered medical knowledge graph and a QA system based on it. Knowledge graph construction, automatic Q&A, KG-based automatic Q&A. A disease-centered knowledge graph in the medical field on a certain scale, and completing automatic Q&A and analysis services with this knowledge graph.
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions โ with one command.
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
Deep neural network to extract intelligent information from invoice documents.
C-OCR is a self-developed OCR project by Ctrip, mainly including recognition of travel-related documents and materials such as ID cards, passports, train tickets, visas, etc. The project consists of 4 parts: rejection, detection, recognition, and post-processing.
Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT Chinese entity recognition and relation extraction
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
Extract structured data and insights from documents using LLMs and decision models
A passive information leakage detection tool based on Chrome and Firefox plugins
This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.
Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)
Tosint is a Telegram OSINT tool that extracts actionable intelligence from bot tokens and chat IDs for security investigations.
A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments
Generate a comprehensive review from an arXiv paper, then turn it into a blog post. This project powers the website below for the HuggingFace's Daily Papers (https://huggingface.co/papers).
The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set the default openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. (sometimes, the official is too crowded and slow)
Uscrapper Vanta: Dive deeper into the web with this powerful open-source tool. Extract valuable insights with ease and efficiency, from both surface and deep web sources. Empower your data mining and analysis with Vanta's advanced capabilities. Fast, reliable, and user-friendly, Uscrapper Vanta is the ultimate choice for researchers and analysts.
Given a scholarly PDF, extract figures, tables, captions, and section titles.
Science Parse parses scientific papers (in PDF form) and returns them in structured form.
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
Paper XMind Note Generation Tool, converts paper PDFs through ChatGPT into concise XMind notes with images and formulas, improving paper reading efficiency.
Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing
RomBuster is a router exploitation tool that allows to disclosure network router admin password.
Frequently Asked Questions
What is the most popular #information-extraction repository on GitHub?
The top ranked open source #information-extraction project on GitHub is PaddlePaddle/PaddleNLP with 13,000 stars. Easy-to-use and powerful LLM and SLM library with awesome model zoo.
Which programming languages are most used in #information-extraction repositories?
Among the top ranked #information-extraction projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Java, HTML.
How is the #information-extraction repository ranking calculated?
We track 42 active open source repositories tagged with #information-extraction (500+ stars), totaling 83,368 stars with an average of 1,984 stars per repository. Rankings update daily from the GitHub API.