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 2,810,379 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
ford_aspire_distributor is a model of automobile 1111 06-jul-2018 98.7  
compressed_natural_gas is a weapon 1111 06-jul-2018 98.2  
florence_dupont_employees__federal_credit_union is a credit union 1111 06-jul-2018 100.0  
two_fast_food is a parlour game 1111 06-jul-2018 100.0  
justice_peter_cory is a judge 1111 06-jul-2018 98.3  
dept is a synonym for administration 1111 06-jul-2018 93.8  
raptors is a sports team that plays against cavaliers 1111 06-jul-2018 99.9  
beds is often found in big_rooms 1111 06-jul-2018 100.0  
brain_maps_to_mechanisms__neural_circuit_molecular_architecture is part of joint_department_of_neurobiology_and_center_for_the_neural_basis_of_cognition_and_systems_neuroscience_institue_seminar 1116 12-sep-2018 100.0  
cells is a subpart of the body within umbilical_cord 1111 06-jul-2018 100.0