http://semanticvoid.com/blog extracting the semantics from the void Sat, 28 Jan 2012 05:39:00 +0000 hourly 1 http://wordpress.org/?v=3.0.4 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-183 Hamsalekha Sr Sat, 28 Jan 2012 05:39:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-183 can i get the perl code for finding cosine similarity of two documents on a windows machine? can i get the perl code for finding cosine similarity of two documents on a windows machine?

]]> http://semanticvoid.com/blog/2011/09/21/wyciwys/#comment-182 Anonymous Fri, 20 Jan 2012 17:40:00 +0000 http://semanticvoid.com/blog/?p=659#comment-182 Wow.... http://www.rosesandgifts.com Wow….
http://www.rosesandgifts.com

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-156 Rashmileos Tue, 01 Nov 2011 01:07:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-156 If I have to find cosine similarity between a query and a document, Should I consider all words in the document? Or just the words which appear in the query? Thanks. If I have to find cosine similarity between a query and a document, Should I consider all words in the document? Or just the words which appear in the query?
Thanks.

]]> http://semanticvoid.com/blog/2011/02/24/speed-gun-for-spam/#comment-136 asanandan anandan Fri, 06 May 2011 12:11:00 +0000 http://semanticvoid.com/blog/2011/02/24/#comment-136 This is useful too. ok . n This is useful too. ok . n

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-143 Antoine Imbert Wed, 27 Apr 2011 03:34:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-143 If the norm of the vector representing the first document is A LOT smaller than the norm of the vector representing the second document, then your documents have a VERY different size. All the magic of the Cosine Similarity is to abstract the size of the documents. You are interested in the similarity of the topic of the contents, not in the similarity of the size of the contents. If the norm of the vector representing the first document is A LOT smaller than the norm of the vector representing the second document, then your documents have a VERY different size. All the magic of the Cosine Similarity is to abstract the size of the documents. You are interested in the similarity of the topic of the contents, not in the similarity of the size of the contents.

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-76 Antoine Imbert Wed, 27 Apr 2011 03:34:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-76 If the norm of the vector representing the first document is A LOT smaller than the norm of the vector representing the second document, then your documents have a VERY different size. All the magic of the Cosine Similarity is to abstract the size of the documents. You are interested in the similarity of the topic of the contents, not in the similarity of the size of the contents. If the norm of the vector representing the first document is A LOT smaller than the norm of the vector representing the second document, then your documents have a VERY different size. All the magic of the Cosine Similarity is to abstract the size of the documents. You are interested in the similarity of the topic of the contents, not in the similarity of the size of the contents.

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-142 Yaroslav Bulatov Mon, 14 Mar 2011 05:39:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-142 An interesting variation on cosine similarity is the "Fisher metric on multinomial manifold". The idea is to treat documents as multinomial probability distributions, use KL divergence to define distance for pair of infinitesimally close distributions and take shortest path integral to define distance for arbitrary pair of distributions. Surprisingly, this has a simple closed form. It looks like cosine similarity, except you take square roots of relative frequencies, see formula 17.9 in http://yaroslavvb.com/upload/save/lebanon-axiomatic.pdf An interesting variation on cosine similarity is the “Fisher metric on multinomial manifold”. The idea is to treat documents as multinomial probability distributions, use KL divergence to define distance for pair of infinitesimally close distributions and take shortest path integral to define distance for arbitrary pair of distributions. Surprisingly, this has a simple closed form. It looks like cosine similarity, except you take square roots of relative frequencies, see formula 17.9 in http://yaroslavvb.com/upload/save/lebanon-axiomatic.pdf

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-75 Yaroslav Bulatov Mon, 14 Mar 2011 05:39:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-75 An interesting variation on cosine similarity is the "Fisher metric on multinomial manifold". The idea is to treat documents as multinomial probability distributions, use KL divergence to define distance for pair of infinitesimally close distributions and take shortest path integral to define distance for arbitrary pair of distributions. Surprisingly, this has a simple closed form. It looks like cosine similarity, except you take square roots of relative frequencies, see formula 17.9 in http://yaroslavvb.com/upload/save/lebanon-axiomatic.pdf An interesting variation on cosine similarity is the “Fisher metric on multinomial manifold”. The idea is to treat documents as multinomial probability distributions, use KL divergence to define distance for pair of infinitesimally close distributions and take shortest path integral to define distance for arbitrary pair of distributions. Surprisingly, this has a simple closed form. It looks like cosine similarity, except you take square roots of relative frequencies, see formula 17.9 in http://yaroslavvb.com/upload/save/lebanon-axiomatic.pdf

]]> http://semanticvoid.com/blog/2011/02/24/speed-gun-for-spam/#comment-135 Tweets that mention a speed gun for spam « Semantic Void -- Topsy.com Fri, 25 Feb 2011 17:31:04 +0000 http://semanticvoid.com/blog/2011/02/24/#comment-135 [...] This post was mentioned on Twitter by anand kishore, Will Fitzgerald. Will Fitzgerald said: RT @semanticvoid: a speed gun for spam http://dlvr.it/HWmFz [blog post] [...] [...] This post was mentioned on Twitter by anand kishore, Will Fitzgerald. Will Fitzgerald said: RT @semanticvoid: a speed gun for spam http://dlvr.it/HWmFz [blog post] [...]

]]> http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-139 diya Thu, 28 Oct 2010 04:21:00 +0000 http://semanticvoid.com/blog/2007/02/23/similarity-measure-cosine-similarity-or-euclidean-distance-or-both/#comment-139 hi its me diya, i have a question that is sample correlation coeffient is equal to the cosine vector?? if it is then how? have you any idea about this or any solution?? i need your advise.. plz let me know.. hi its me diya, i have a question that is sample correlation coeffient is equal to the cosine vector?? if it is then how? have you any idea about this or any solution?? i need your advise.. plz let me know..

]]>