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 2,884,351 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
hieronymus_bosch is a visual artist 1080 02-dec-2017 100.0  
bob_wilson_memorial_hospital is a hospital 1080 02-dec-2017 100.0  
n15_92 is a term used by physicists 1081 03-dec-2017 91.8  
patrick_barr is a North American person 1080 02-dec-2017 100.0  
pkk_terrorism is a visual art movement 1081 03-dec-2017 92.8  
nation participated in the event crimes 1080 02-dec-2017 99.2  
president_obama is a U.S. politician who is a member of the political group house 1084 07-dec-2017 100.0  
smart is a specific automobile maker dealer in canada 1081 03-dec-2017 100.0  
the sports team france was the winner of n2000_european_cup 1085 09-dec-2017 100.0  
jimmy_chamberlin is a musician who is part of smashing_pumpkins 1084 07-dec-2017 93.8