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 3,807,819 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
phone_casino is an item found on a table 1039 07-feb-2017 98.9  
regional_solid_waste_master_plan is something 1040 14-feb-2017 96.9  
first_federal_savings_and_loan_association is a credit union 1039 07-feb-2017 100.0  
new_york_lieutenant_governor is a kind of office held by a politician 1039 07-feb-2017 100.0  
sliced_mushrooms_in_merlot_sauce is a fungus 1039 07-feb-2017 91.9  
aphids is an invertebrate animal that feeds on plants 1040 14-feb-2017 100.0  
pants is a clothing item to go with style_shirt 1039 07-feb-2017 100.0  
ball is a kind of equipment for the sport netball 1040 14-feb-2017 98.4  
chicago_o_hare is an airport in the city chicago 1043 24-mar-2017 100.0  
rose is a person who graduated from the university college 1040 14-feb-2017 98.4