tanyuqian/knowledge-harvest-from-lms
ACL 2023 (Findings) - BertNet: Harvesting Knowledge Graphs from Pretrained Language Models
This project helps researchers and knowledge engineers automatically build and expand knowledge graphs. You provide a small set of relation definitions (like "A is capable of but not good at B"), and it generates new, complex factual statements and relationships (knowledge tuples) from large language models. The output is a new knowledge graph containing these extracted relationships, useful for enriching existing graphs or creating new ones for specific domains.
107 stars. No commits in the last 6 months.
Use this if you need to rapidly construct or expand a knowledge graph for a new domain or with nuanced relationships, without extensive manual annotation or large existing datasets.
Not ideal if you require knowledge graphs built solely from human-curated data or need to extract facts from specific, structured documents rather than general language model knowledge.
Stars
107
Forks
17
Language
Python
License
—
Category
Last pushed
Jul 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/tanyuqian/knowledge-harvest-from-lms"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
stair-lab/kg-gen
[NeurIPS '25] Knowledge Graph Generation from Any Text
DerwenAI/textgraphs
TextGraphs + LLMs + graph ML for entity extraction, linking, ranking, and constructing a lemma graph
alisonmitchell/Biomedical-Knowledge-Graph
Information extraction from unstructured text to build a knowledge graph using techniques from...