NELL: Never-Ending Language Learning

Read the Web
Browse the Knowledge Base!

Can computers learn to read? We think so. "Read the Web" is a research project that attempts to create a computer system that learns over time to read the web. Since January 2010, our computer system called NELL (Never-Ending Language Learner) has been running continuously, attempting to perform two tasks each day:

So far, NELL has accumulated over 50 million candidate beliefs by reading the web, and it is considering these at different levels of confidence. NELL has high confidence in 2,761,964 of these beliefs — these are displayed on this website. It is not perfect, but NELL is learning. You can track NELL's progress below or @cmunell on Twitter, browse and download its knowledge base, read more about our technical approach, or join the discussion group.

Recently-Learned Facts Follow NELL on Twitter

instance iteration date learned confidence
rockets is a sports team 991 27-apr-2016 100.0  
packing_tissue_paper is an office supply 991 27-apr-2016 91.0  
black___gold is a visualizable attribute 992 02-may-2016 100.0  
north_bay is a visualizable scene 991 27-apr-2016 100.0  
vital_issues is an area of study within the field of machine learning 991 27-apr-2016 100.0  
holly_madison is a person who has residence in the state or province alaska 991 27-apr-2016 100.0  
camp_nou is the home venue for the sports team barcelona 996 27-may-2016 100.0  
alexander_ovechkin is an athlete coached by bruce_boudreau 996 27-may-2016 100.0  
david_boston plays in the league nfl 996 27-may-2016 94.7  
dairy is an agricultural product coming from small_ruminants 992 02-may-2016 93.8