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 2,810,379 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
federal_advisory_committee is a political organization that is not part of the government 1111 06-jul-2018 100.0  
cardamom_lemon_peel_muffins is a baked good 1111 06-jul-2018 100.0  
turkish_elections is an election 1111 06-jul-2018 98.4  
sportsmens_restaurant___taverna is a restaurant 1111 06-jul-2018 99.9  
entrusting is a physical action 1112 24-jul-2018 90.5  
states is a state or province located in the geopolitical location china 1111 06-jul-2018 98.4  
mike_anderson is a visual artist in the field of paintings 1116 12-sep-2018 93.8  
gov__sarah_palin is a U.S. politician endorsed by the U.S. politician sen__john_mccain 1113 15-aug-2018 100.0  
duck is an animal that eats goat_cheese 1116 12-sep-2018 100.0  
battersea_power_station is a tourist attraction in the city central_london 1116 12-sep-2018 100.0