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 2,180,254 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
food_home is a non-profit organization 881 24-oct-2014 100.0  
buena_vista is a city 881 24-oct-2014 96.9  
fig_3 is an item often found in a bedroom 881 24-oct-2014 95.1  
n1988_olympic_stub is an instance of the olympics 883 02-nov-2014 99.8  
voting_software is a tool 884 08-nov-2014 99.1  
eyes is a subpart of the body within system002 881 24-oct-2014 100.0  
alexis was born in the city york 886 21-nov-2014 96.9  
jon_voight is the father of angelina_jolie 886 21-nov-2014 100.0  
point_defiance_zoo___aquarium is an aquarium in the city tacoma 886 21-nov-2014 100.0  
ford is a company that produces sierra 886 21-nov-2014 99.6