- author = "Rudi Cilibrasi and Paul M. B. Vitanyi",
- title = "Automatic Meaning Discovery Using {Google}",
- year = "2005",
- number = "cs.CL/0412098",
- month = "15 " # mar,
- note = "v2",
- keywords = "genetic algorithms, genetic programming, randomised hill-climbing, SVM, support vector machines, complearn, Computation and Language, Artificial Intelligence, Databases, Information Retrieval, Learning",
-
URL = "
http://www.arxiv.org/abs/cs.CL/0412098",
-
URL = "
http://homepages.cwi.nl/~paulv/papers/amdug.pdf",
- abstract = "We have found a method to automatically extract the meaning of words and phrases from the world-wide-web using Google page counts. The approach is novel in its unrestricted problem domain, simplicity of implementation, and manifestly ontological underpinnings. The world-wide-web is the largest database on earth, and the latent semantic context information entered by millions of independent users averages out to provide automatic meaning of useful quality. We demonstrate positive correlations, evidencing an underlying semantic structure, in both numerical symbol notations and number-name words in a variety of natural languages and contexts. Next, we demonstrate the ability to distinguish between colours and numbers, and to distinguish between 17th century Dutch painters; the ability to understand electrical terms, religious terms, and emergency incidents; we conduct a massive experiment in understanding WordNet categories; and finally we demonstrate the ability to do a simple automatic English-Spanish translation.",
-
notes = "ACM-class: I.2.4; I.2.7
Date (v1): Tue, 21 Dec 2004 16:05:36 GMT (127kb,S) Date (revised v2): Tue, 15 Mar 2005 16:53:43 GMT (58kb)
cited by \cite{graham-rowe:2005:complearn}
Code http://www.complearn.org/",
- size = "31 pages",
