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 2,103,385 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
m___t_bank is a credit union 875 04-oct-2014 100.0  
protected_birds is a vertebrate 874 25-sep-2014 99.7  
dental_chair is an item found on the floor 877 10-oct-2014 100.0  
lamb_sausage is a type of meat 875 04-oct-2014 100.0  
clifton_forge_city__sheriff is a kind of office held by a politician 874 25-sep-2014 98.1  
chang_yung_fa is the CEO of evergreen 879 19-oct-2014 93.8  
charleston is a city that lies on the river cooper_industries 875 04-oct-2014 100.0  
massachusetts_general is a hospital in the city boston 879 19-oct-2014 100.0  
subaru makes the automobile mazda 877 10-oct-2014 93.8  
league_of_nations is headquartered in the city geneva 879 19-oct-2014 100.0