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
ad_dakhla is a state or a province	1111	06-jul-2018	98.4
east_finchley_cemetery is a place of worship	1111	06-jul-2018	99.9
hard_rock_las_vegas_summer_stage is a building	1111	06-jul-2018	96.9
song_huong_restaurant is a restaurant	1111	06-jul-2018	100.0
micro_finance is an academic field	1111	06-jul-2018	100.0
esau is the father of aaron	1116	12-sep-2018	96.9
the country jamaica uses the currency dollars	1116	12-sep-2018	100.0
china is a country located in the geopolitical location other_countries	1111	06-jul-2018	100.0
chris_lee was born in the city new_york	1116	12-sep-2018	100.0
klamath_mountains is a mountain in the state or province oregon	1116	12-sep-2018	100.0