I figured out that there are already java API's written for this and available. LucQE has that :
QueryExpansion.expandQuery(java.lang.String queryStr, org.apache.lucene.search.Hits hits, java.util.Properties prop) which returns the expanded query (will have centroid) Grant Ingersoll-6 wrote: > > You could use Term Vectors (TVs) to do this, but I don't know of any > existing code for it. Might be a good contrib module, though. > Search this list or see Lucene In Action or I have some TV sample > code at http://www.cnlp.org/apachecon2005/ > > You might also check the Carrot2 project, which has a number of > clustering algorithms and some Lucene support, although I don't know > if it does specifically what you want. > > On Apr 2, 2007, at 10:14 PM, Lokeya wrote: > >> >> Hi All, >> >> I have queried and have got a HITS object which is a collection of >> documents. I want to find out the centroid of these documents. >> Centroid = >> Top Most 35(for eg)common terms across all the documents in the HITS >> object. >> >> Is there any API in Lucene for this? >> >> Thanks in Advance. >> -- >> View this message in context: http://www.nabble.com/How-to- >> calculate-centroid-from-HITS--tf3509432.html#a9802563 >> Sent from the Lucene - Java Users mailing list archive at Nabble.com. >> >> >> --------------------------------------------------------------------- >> To unsubscribe, e-mail: [EMAIL PROTECTED] >> For additional commands, e-mail: [EMAIL PROTECTED] >> > > -------------------------- > Grant Ingersoll > Center for Natural Language Processing > http://www.cnlp.org > > Read the Lucene Java FAQ at http://wiki.apache.org/jakarta-lucene/ > LuceneFAQ > > > > --------------------------------------------------------------------- > To unsubscribe, e-mail: [EMAIL PROTECTED] > For additional commands, e-mail: [EMAIL PROTECTED] > > > -- View this message in context: http://www.nabble.com/How-to-calculate-centroid-from-HITS--tf3509432.html#a10091264 Sent from the Lucene - Java Users mailing list archive at Nabble.com. --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
