peng-yiwen/WiKC
A cleaned version of Wikidata taxonomy - Refined using Large Language Models
This project helps knowledge engineers and data scientists refine and clean large-scale taxonomies, specifically those derived from Wikidata. It takes raw Wikidata taxonomy data and processes it using large language models and graph mining techniques to produce a more accurate and structured taxonomy. The cleaned taxonomy can be used for various applications requiring precise hierarchical knowledge.
No commits in the last 6 months.
Use this if you need to create or improve a structured, clean, and semantically consistent taxonomy from a large, noisy knowledge base like Wikidata for use in knowledge graphs, search, or semantic understanding applications.
Not ideal if you're looking for a simple keyword extraction tool or a small, domain-specific ontology builder rather than a large-scale, automated taxonomy refinement pipeline.
Stars
11
Forks
—
Language
HTML
License
MIT
Category
Last pushed
Aug 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/peng-yiwen/WiKC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ananthanarayanan431/Langchain-Projects-LLM
Various projects using Large Language Model (GPT & LLAMA) other open source model from...
deepset-ai/haystack-home
Website for Haystack, the open source LLM framework
astronomer/ask-astro
An end-to-end LLM reference implementation providing a Q&A interface for Airflow and Astronomer
jndiogo/sibila
Extract structured data from local or remote LLM models
Quhaoh233/ChatEV
ChatEV: Predicting electric vehicle charging demand as natural language processing