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
homestead_road_church_of_christ is a religion 1111 06-jul-2018 100.0  
matrix_vector_multiplication is a scientific term 1111 06-jul-2018 100.0  
reindeer_lake is a lake 1111 06-jul-2018 100.0  
marginal_mandibular_branches_of_facial_nerve is a nerve 1111 06-jul-2018 97.9  
hiking_and_walking is a sport 1111 06-jul-2018 99.9  
sen__john_mccain is a U.S. politician who is a member of the political group house 1113 15-aug-2018 93.8  
peppers is an agricultural product produced in __america 1116 12-sep-2018 99.2  
air_madagascar is headquartered in the city paris 1116 12-sep-2018 100.0  
chevrolet is a specific automobile maker dealer in missouri 1114 25-aug-2018 100.0  
cincinnati is the capital city of the state or province oh 1116 12-sep-2018 100.0