Tag
This paper utilizes NLP techniques such as NER and BERTopic, along with Neo4j, to extract, classify, and visualize knowledge from translated ancient Indian medical texts, enhancing accessibility and digital preservation.
HyperExtract is an LLM-powered framework that converts unstructured documents into structured knowledge graphs, hypergraphs, and lists, simplifying knowledge extraction and management.
HERMES is a scalable multi-agent framework for extracting structured knowledge from ultra-long scientific documents in geoscience, achieving high accuracy and sixfold efficiency improvement over manual methods.
The author describes how they built a Claude skill to extract Ray Dalio's Big Cycle framework from a video transcript, using a structured extraction prompt and organizing the output into a SKILL.md. The article shares their step-by-step process for turning video knowledge into runnable AI workflows.
book-to-skill is an open-source tool that converts PDFs, ePubs, and long documents into structured SKILL.md files for AI coding agents like Claude Code and Cursor, enabling agents to permanently apply book knowledge during coding sessions.
An AI-powered tool for extracting knowledge and generating summaries from PDF books page by page.
A Python script that can automatically parse PDF book content, extract key knowledge points, and generate Markdown-format summaries, aiming to improve reading and knowledge organization efficiency.
QuantMind is an open-source framework for intelligent knowledge extraction and retrieval in quantitative finance. It can automatically fetch unstructured content like papers and news, build a queryable structured knowledge base, and support natural language retrieval.
This paper constructs the first large-scale citation graph from 100.7 million Ukrainian court decisions, extracting over 500 million citation links. It demonstrates that the citation structure can automatically recover legal domain boundaries and predict legislative importance with near-perfect accuracy, and releases the pipeline and data as open resources.
This paper proposes the Experience Compression Spectrum, a unifying framework that integrates agent memory, skill discovery, and rule-based systems along a single axis of increasing compression (5-20× for episodic memory, 50-500× for procedural skills, 1000×+ for declarative rules). The work identifies a critical gap—the 'missing diagonal'—showing that existing systems operate at fixed compression levels without adaptive cross-level support, and articulates design principles for scalable, full-spectrum agent learning systems.
Hyper-Extract is an open-source CLI tool that uses LLMs to extract structured knowledge from unstructured documents, supporting various output formats like knowledge graphs and hypergraphs.