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 2,870,383 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
swahili is a language 1018 06-oct-2016 100.0  
musculoskeletal_system is a bone 1018 06-oct-2016 90.1  
kpnx_tv is a radio station 1018 06-oct-2016 100.0  
jean_delannoy is a commedian 1016 21-sep-2016 93.8  
book_art is a kind of media 1018 06-oct-2016 97.4  
ford is a company that produces windstar 1018 06-oct-2016 100.0  
steve is a person who died at the age of 3 1021 18-oct-2016 99.6  
mice001 is an animal that can develop cardiomyopathy 1019 10-oct-2016 100.0  
villa_coronado_park is a generalization of temple_of_the_reclining_buddha 1019 10-oct-2016 100.0  
kansas_city_star is related to www_kansascity_com 1021 18-oct-2016 100.0