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 2,884,737 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
ska_punk is a genre of music 1018 06-oct-2016 100.0  
western_four_presidents_lodge is a trail 1018 06-oct-2016 98.7  
class_holders is a machine-learning conference 1018 06-oct-2016 99.3  
decirme is a currency 1018 06-oct-2016 92.9  
salmon_experience is a vertebrate 1019 10-oct-2016 96.8  
father001 is the parent of christ_jesus 1019 10-oct-2016 99.2  
congo_river empties into river congo 1022 23-oct-2016 100.0  
voa is a company headquartered in the city washington_d_c_ 1022 23-oct-2016 100.0  
studio_museum_harlem is a museum in the city new_york_city_metropolitan_area 1022 23-oct-2016 98.4  
the sports team yankees was the winner of n1923_world_series 1022 23-oct-2016 100.0