I did some work about 5 years ago, where we took a dump of Wikipedia, and computed the Jensen-Shannon divergence between the documents. The idea was that two documents with small JS are closely related in meaning. We were trying to see if the induced network from JS-divergence had similar network properties to network of networks between words in the online dictionary WordNet.
The short answer was - they don't. Then funding ran out, and I moved onto other things :). Cheers On Thu, Feb 07, 2013 at 10:09:25AM -0700, Ron Newman wrote: > I'm in need of some semantic analysis tools, thought this might be a good > place to start. In 1992 I worked with a fellow from Australia who I've > lost contact with who did keyword analysis including their proximity to > each other. He could generate an abstract to a paper that was pretty good > and represented meaning. > > With all the work in Semantic Web, RDF, etc., there have got to be great > tools out there that I can get educated about. Suggestions welcome. > > -- > Ron Newman, Founder > MyIdeatree.com <http://www.Ideatree.us> > ============================================================ > FRIAM Applied Complexity Group listserv > Meets Fridays 9a-11:30 at cafe at St. John's College > to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com -- ---------------------------------------------------------------------------- Prof Russell Standish Phone 0425 253119 (mobile) Principal, High Performance Coders Visiting Professor of Mathematics [email protected] University of New South Wales http://www.hpcoders.com.au ---------------------------------------------------------------------------- ============================================================ FRIAM Applied Complexity Group listserv Meets Fridays 9a-11:30 at cafe at St. John's College to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
