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
n1995_buenos_aires_grand_prix is a sporting event 1111 06-jul-2018 100.0  
john_r__erickson_4_5_3_0_736en_fahrenheit_451 is a European person 1111 06-jul-2018 100.0  
frangelico_cake is a baked good 1111 06-jul-2018 100.0  
cranberry_nut is a fruit 1111 06-jul-2018 98.8  
n2_calendar_days is a non-sports, non-electronic game 1111 06-jul-2018 94.1  
gore is a U.S. politician endorsed by the U.S. politician mr__bush 1112 24-jul-2018 98.4  
wfxg is a TV affiliate of the network fox 1116 12-sep-2018 100.0  
spiders is an animal that is a kind of animals 1111 06-jul-2018 100.0  
rsa_in_the_real_world occurrs in the building gates___hillman_centers 1116 12-sep-2018 100.0  
phillips is a person who graduated from the university college 1111 06-jul-2018 98.4