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 2,517,789 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
faith_montgomery_fellowship is a religion 940 21-jul-2015 95.9  
smooth_flower_spider is an invertebrate 942 04-aug-2015 100.0  
n29_1 is a performance metric used by machine-learning scientists 940 21-jul-2015 100.0  
drivers_companies is sports equipment 944 11-aug-2015 92.1  
operations_team_lead is a job position 940 21-jul-2015 93.5  
products is a generalization of palm_oil 940 21-jul-2015 100.0  
lexus is a company that has an office in the country uk 940 21-jul-2015 100.0  
chung_ju_yung created the organziation hyundai_motor 941 25-jul-2015 100.0  
the final score of the sports game wembley was 3-2 945 13-aug-2015 100.0  
charleston is a city that lies on the river cooper_industries 944 11-aug-2015 100.0