Re: Measuring document similarity

2012-03-12 Thread Koji Sekiguchi
(12/03/13 2:38), Hassane Cabir wrote: Hi guys, I'm using Lucene for my project and I need to calcule how similar two (or more) documents are, using TFIDF. How to get TFIDF with lucene? Any insights on this? Solr has TermVectorComponent which can return tf, df and tf-idf of each term in a docu

Measuring document similarity

2012-03-12 Thread Hassane Cabir
Hi guys, I'm using Lucene for my project and I need to calcule how similar two (or more) documents are, using TFIDF. How to get TFIDF with lucene? Any insights on this? Thank you for your support . -- Hassane