Read the Web
Research Project at Carnegie Mellon University

NELL: Never-Ending Language Learning

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:

• First, it attempts to "read," or extract facts from text found in hundreds of millions of web pages (e.g., playsInstrument(George_Harrison, guitar)).
• Second, it attempts to improve its reading competence, so that tomorrow it can extract more facts from the web, more accurately.

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

instance	iteration	date learned	confidence
quiet_street is a visualizable object	1111	06-jul-2018	98.9
postcapillary_venule is a vein	1111	06-jul-2018	95.9
downtown_san_francisco is a visualizable scene	1111	06-jul-2018	99.7
_13 is a year	1111	06-jul-2018	100.0
potter_wasp is an arthropod	1111	06-jul-2018	100.0
tim_burton directed the movie demon_barber_of_fleet_street	1115	03-sep-2018	96.9
roissy_charles_de_gaulle is a generalization of temple_of_the_reclining_buddha	1114	25-aug-2018	100.0
usc hired carroll	1113	15-aug-2018	96.9
san_diego_padres is a sports team that won the division	1115	03-sep-2018	93.8
richard is a U.S. politician who holds the office of u_s__president	1116	12-sep-2018	99.2