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
of_the_pulaski_bridge is a bridge 1111 06-jul-2018 96.6  
anthony_john_denison is a Canadian person 1111 06-jul-2018 100.0  
gourmet_gift_baskets is sports equipment 1111 06-jul-2018 96.7  
raoul_hausmann is a visual artist 1111 06-jul-2018 92.9  
international_red_cross is a non-profit organization 1111 06-jul-2018 100.0  
president_reagan is a U.S. politician who holds the office of assistant_secretary 1112 24-jul-2018 99.2  
suzuki is a specific automobile maker dealer in tucson 1114 25-aug-2018 100.0  
n3_30pm is the time of the event child_in_involved_in_collision_in_which_mother_was_killed_moved_to_belfast_hospital 1116 12-sep-2018 100.0  
browns_stadium is a tourist attraction in the city cleveland 1116 12-sep-2018 100.0  
koji_uehara plays the sport baseball 1116 12-sep-2018 99.9