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 2,101,275 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
city_bank_and_trust_company_of_moberly is a bank 868 02-sep-2014 100.0  
saint_petersburg_junior_college is a train station 868 02-sep-2014 100.0  
andrea_strachan is a visual artist 869 05-sep-2014 95.3  
christian_social_party is a terrorist organization 868 02-sep-2014 99.8  
jewelry_lapidary is a personal care product 869 05-sep-2014 91.9  
the sports leage mlb uses the venue rfk_memorial_stadium 871 14-sep-2014 96.9  
brooklyn_academy_of_music is a museum in the city new_york_city 873 19-sep-2014 99.6  
nissan is a specific automobile maker dealer in san_diego 869 05-sep-2014 100.0  
national_league participated in the event series 868 02-sep-2014 98.4  
metropolitan_life_insurance is a company headquartered in the city new_york_city 873 19-sep-2014 93.8