Read The Web

Research Project at Carnegie Mellon University

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 1,912,218 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 FactsFollow NELL on Twitter

instanceiterationdate learnedconfidence
knjd_lp is a TV station70428-feb-201393.2
arena_at_southeastern_ky_expo_complex is a stadium or event venue70428-feb-201394.3
fishbowls is a fish70604-mar-201397.3
newsweek is a magazine70910-mar-2013100.0
hanger_steak is a type of meat70910-mar-201393.8
chicken is an agricultural product that is usually cut into inch_cubes70604-mar-201398.4
eric is a musician who plays the lead_vocals70705-mar-201398.4
maritime_aquarium is an aquarium in the city norwalk70910-mar-2013100.0
fleet_center is a stadium or event venue located in the city boston70910-mar-201393.8
english is a language used in the university rutgers_university


0 yorum: