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
baby_tableware is an item found on a table	1111	06-jul-2018	99.5
nasty_biting_flies is an invertebrate	1111	06-jul-2018	97.3
party_of_democratic_action_of_croatia is a political party	1111	06-jul-2018	100.0
rock___pop is a genre of music	1111	06-jul-2018	99.5
locked_bedroom_door is an item often found in a hallway	1111	06-jul-2018	99.8
joseph_conrad wrote the book the_heart_of_darkness	1111	06-jul-2018	96.9
shepherds_bush is a park in the city central_london	1116	12-sep-2018	96.9
states is a state or province located in the geopolitical location israel	1114	25-aug-2018	100.0
jeff_gordon is an athlete who beat carl_edwards	1115	03-sep-2018	100.0
blue_jays is a sports team that plays the sport baseball	1116	12-sep-2018	100.0