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 2,155,106 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
main_villa is a kind of room 881 24-oct-2014 90.7  
tea_coffee_tray is a legume 881 24-oct-2014 91.4  
paul_wilcox is a journalist 877 10-oct-2014 90.0  
mdm2_e3_ligase is a protein 881 24-oct-2014 90.3  
geo_cars is a kind of vehicle 878 16-oct-2014 99.5  
hoxton_square is a tourist attraction in the city london 881 24-oct-2014 100.0  
metrorail is a transportation system located in the city los_angeles 881 24-oct-2014 100.0  
siskiyou_mountains is a mountain in the state or province oregon 881 24-oct-2014 100.0  
buzios is a city also known as rio 880 21-oct-2014 100.0  
jay is a person who moved to the state california 881 24-oct-2014 93.8