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 3,027,643 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
jose_diaz coaches a sports team 1030 09-dec-2016 100.0  
chicken_weight is a type of meat 1031 15-dec-2016 93.1  
passive_money is a fungus 1030 09-dec-2016 99.6  
occam_pi is a programming language 1034 05-jan-2017 98.4  
lower_level_hallway is a kind of room 1033 29-dec-2016 99.5  
outdoor_activities is a generalization of snowboarding 1033 29-dec-2016 96.9  
anadarko_petroleum is a company also known as apc 1030 09-dec-2016 100.0  
chicken001 is an animal that eats spinach_cream_sauce 1034 05-jan-2017 93.8  
viral is a bacteria that causes infections 1031 15-dec-2016 100.0  
westinghouse is an organization known by the acronym westinghouse_electric_corporation 1034 05-jan-2017 100.0