- From: Steve Harris <S.W.Harris@ecs.soton.ac.uk>
- Date: Fri, 1 Aug 2003 10:14:56 +0100
- To: "Judson, Ross" <rjudson@managedobjects.com>
- Cc: www-rdf-interest@w3.org
On Thu, Jul 31, 2003 at 03:21:49 -0400, Judson, Ross wrote: > Now imagine that someone builds a big corpus of URIs, and starts to > categorize them. Someone like, say, Google, or DMOZ. The text of each > URI is used to create Bayesian classifiers. We have been doing something similar in the AKT project, using Bayesian classifiers to categorise unannotated that appear in our KB against the ACM computer science taxonomy: http://www.aktors.org/technologies/ClassAKT/ Running the training algorithm takes quite a while, but the results are pretty good. - Steve
Received on Friday, 1 August 2003 05:15:00 UTC