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
famous_facebook is a website	1111	06-jul-2018	93.1
gmc_yukon_cars is a kind of vehicle	1111	06-jul-2018	99.4
light_lavender_violet is a color	1112	24-jul-2018	99.2
tile_ceilings is something found in or on buildings	1111	06-jul-2018	99.3
complete_snow is software used by machine-learning scientists	1112	24-jul-2018	99.6
kuznetsova is an athlete who beat williams	1115	03-sep-2018	96.9
fortis is a bank that bought abn_amro	1114	25-aug-2018	100.0
denver is the capital city of the state or province colorado	1116	12-sep-2018	100.0
salmon is a fish that can be served with the food introduction in a meal (or dish)	1116	12-sep-2018	99.9
uppsala_university is a sports team that plays in the league international	1116	12-sep-2018	100.0