Skip to content
RAG Repo

NELL (Never-Ending Language Learner)

NELL runs as a continuous experiment: it reads web pages, proposes new facts about entities and how they relate, and uses what it already knows to judge and improve the next round of extractions. Over years of running, this has grown into a large store of candidate beliefs, each with a confidence score reflecting how sure the system is.

The knowledge base is published for download, so you can browse or reuse the extracted facts. Because the beliefs come from automatic reading rather than human curation, quality varies, and the confidence scores matter when you decide which facts to trust.

For RAG, NELL is mainly of research interest: a case study in learning structured knowledge from text at scale, and a source of web-derived facts if you are willing to filter by confidence.

knowledge-graphmachine-learningweb-extractionresearchacademic

Related sources