NELL System
(Redirected from NELL)
Jump to navigation
Jump to search
An NELL System is a open information extraction from text system produced by CMU's Read the Web Research Project.
- AKA: Never-Ending Language Learning.
- Context:
- It can recognize Noun Phrases.
- It can product a Categorized Noun Phrase Dataset. http://rtw.ml.cmu.edu/rtw/nps
- It manages a NELL Knowledge Base, which is a Knowledge Base without an explicit Semantic Data Model.
- It has been running since 2010.
- It can be Inferences.
- It cannot yet make Temporal Inferences (discover Temporal Relations).
- It learns many functions at once (not one at a time) to constrain the search (couples Co-Learning with Multi-View Learning).
- It has extracted massive amounts of machine-readable knowledge with minimal supervision.
- …
- Counter-Example(s):
- ReVerb System.
- SHERLOCK System, requires an ontoloyg
- CYC System.
- See: Machine Reading Task.
References
2012
- (Mitchell, 2012) ⇒ Tom Mitchell. "Never Ending Language Learning." Invited Talk at NAACL Workshop on Knowledge Extraction.
- Tenet 1: Understanding requires a belief system.
We'll never produce natural language understanding systems until we have systems that react to arbitrary sentences by saying one of:
- I understand, and already knew that
- I understand, and didn't know, but accept it.
- I understand, but disagree because ...
- Tenet 2: We'll never really understand learning until we build machines that: learn many different things, over years, and become better learners over time.
- Tenet 1: Understanding requires a belief system.
2011
- Homepage: http://rtw.ml.cmu.edu/rtw/
- 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.
- At present, NELL has accumulated a knowledge base of 518,126 beliefs that it has read from various web pages. 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.
- 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:
- (Wikipedia, 2011) http://en.wikipedia.org/wiki/Never-Ending_Language_Learning
- Never-Ending Language Learning system (NELL) is a semantic machine learning system developed by a research team at Carnegie Mellon University, and supported by grants from DARPA, Google, and the NSF, with portions of the system running on a supercomputing cluster provided by Yahoo!.
2010
- (Carlson et al., 2010) ⇒ Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka, and Tom M. Mitchell. (2010). “Toward an Architecture for Never-Ending Language Learning.” In: Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2010).