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 2,330,396 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
lemuel_s_bean is a fruit 856 22-jul-2014 98.6  
clearview_avenue is a retail store 853 11-jul-2014 100.0  
horse_ridge is a bridge 853 11-jul-2014 99.9  
black_tailed_treecreeper is a plant 853 11-jul-2014 100.0  
marriott_annapolis is a hotel 853 11-jul-2014 91.6  
pne_forum is a stadium or event venue located in the city columbia 857 26-jul-2014 96.9  
animals is an animal that preys on pandas 853 11-jul-2014 98.4  
tyler001 is a person who has attended the school college 856 22-jul-2014 93.8  
mice refers to more than one mouse 854 16-jul-2014 100.0  
west is a city located in the geopolitical location united_kingdom 857 26-jul-2014 96.9