I think that this project will be useful for you: http://lucene-qe.sourceforge.net/ On the other hand you cam implement kullback leibler divergence or similar algoritms usig TermDocs class. This paper can help you to understand the theory: http://portal.acm.org/citation.cfm?doid=366836.366860 http://cat.inist.fr/?aModele=afficheN&cpsidt=15758562 I hope help you jose On Sun, May 18, 2008 at 5:57 AM, Steven A Rowe wrote: > MoreLikeThis, perhaps?: > > > > Steve > > On 05/17/2008 at 10:06 PM, Otis Gospodnetic wrote: >> It doesn't. But do some searching, I know somebody did >> contribute blind reference feedback implementation to Lucene. >> The reference to that contribution must be out there somewhere. >> >> Otis >> -- >> Sematext -- http://sematext.com/ -- Lucene - Solr - Nutch >> >> >> ----- Original Message ---- >> > From: DanaWhite >> > To: general@lucene.apache.org >> > Sent: Saturday, May 17, 2008 10:35:27 AM >> > Subject: Relevence Feedback >> > >> > >> > Hello, >> > >> > I was under the impression Lucene did not come with any relevance >> > feedback implementation, and that you needed to add it yourself. >> > Someone told me Lucene does indeed have relevence feedback included, >> > but I can't seem to find anything to support what this person told me. >> > >> > So I am here to ask the experts, >> > Does Lucene have relevence feedback "out of the box"? >> > >> > Thanks >> > Dana >> > -- >> > View this message in context: >> > http://www.nabble.com/Relevence-Feedback-tp17292431p17292431.html >> > Sent from the Lucene - General mailing list archive at Nabble.com. >> >> > > > > -- José Ramón Pérez Agüera Dept. de Ingeniería del Software e Inteligencia Artificial Despacho 411 tlf. 913947599 Facultad de Informática Universidad Complutense de Madrid