Comments on: EyePlorer : a New Approach to Semantic Search http://www.searchenginejournal.com/eyeplorer-semantic-search/9244/ Tue, 14 Feb 2012 09:28:52 +0000 hourly 1 http://wordpress.org/?v= By: Georg Rehm http://www.searchenginejournal.com/eyeplorer-semantic-search/9244/comment-page-1/#comment-1097398 Georg Rehm Thu, 02 Apr 2009 13:34:24 +0000 http://www.searchenginejournal.com/?p=9244#comment-1097398 Thanks a lot for this very good overview article on eyePlorer.com, we're glad that you enjoy working with the tool. By the way, we're currently implementing several new features to be released in a few weeks. Thanks a lot for this very good overview article on eyePlorer.com, we’re glad that you enjoy working with the tool. By the way, we’re currently implementing several new features to be released in a few weeks.

]]> By: chris http://www.searchenginejournal.com/eyeplorer-semantic-search/9244/comment-page-1/#comment-1096382 chris Tue, 24 Mar 2009 09:17:45 +0000 http://www.searchenginejournal.com/?p=9244#comment-1096382 @mark: Yes that makes sense. The technology looks very poor and crappy. Its based on simple pattern matching and collocation analysis. The technology behind is also based on a simple activation spreading network which produces the k-graphs - the term here is k-matrix. The graphs are static and precalculated. We must calculate the whole graph new if something changes. Also the content base must contain valid text. The system is not be able to search in webpages, cause the lingustic system behind must analyse sentences. Webpages has quite more problematic text patterns. Sentences are not simple to recognize and extract, it is very domain dependend. Also there is not idea yet to prevent spam and SEO stuff.The system also has yet no ability to recognize invalid statements (Subject-Predicate-Object) like "A headset is human". In opposite to the suggestion of the name (vionto == visual ontology) the system does not based on any ontology which follows an official definition. Your problem with "tail" comes from the relevance and the denotation of the term. The term has much different concepts with which the technology behind is not able to work and distinguishable correctly. The system behind has no idea of "tail". "tail" is only a term which is associated with some other terms. Also "tail" is not only a thing but also a verb (to tail after someone, to tail after someone, to keep one's tail up...) @mark: Yes that makes sense. The technology looks very poor and crappy. Its based on simple pattern matching and collocation analysis. The technology behind is also based on a simple activation spreading network which produces the k-graphs – the term here is k-matrix. The graphs are static and precalculated. We must calculate the whole graph new if something changes. Also the content base must contain valid text. The system is not be able to search in webpages, cause the lingustic system behind must analyse sentences. Webpages has quite more problematic text patterns. Sentences are not simple to recognize and extract, it is very domain dependend. Also there is not idea yet to prevent spam and SEO stuff.The system also has yet no ability to recognize invalid statements (Subject-Predicate-Object) like “A headset is human”. In opposite to the suggestion of the name (vionto == visual ontology) the system does not based on any ontology which follows an official definition.

Your problem with “tail” comes from the relevance and the denotation of the term. The term has much different concepts with which the technology behind is not able to work and distinguishable correctly. The system behind has no idea of “tail”. “tail” is only a term which is associated with some other terms. Also “tail” is not only a thing but also a verb (to tail after someone, to tail after someone, to keep one’s tail up…)

]]> By: mark http://www.searchenginejournal.com/eyeplorer-semantic-search/9244/comment-page-1/#comment-1096176 mark Fri, 20 Mar 2009 10:13:56 +0000 http://www.searchenginejournal.com/?p=9244#comment-1096176 my eyes(pots) tell me that this visualization is pretty much a useless toy with nice colors - just like a cake with too much icing. just tried to find something about " tail". all eyespots refer to a single wikipedia page. Clusters make pretty much no sense at all: what's the rationale for a "work" cluster. Some results are completely missing: where is a reference for the Unix tool "tail"???? cf http://en.wikipedia.org/wiki/Tail_(Unix) pretty disappointing in my eyes(pots) mark my eyes(pots) tell me that this visualization is pretty much a useless toy with nice colors – just like a cake with too much icing.

just tried to find something about ” tail”.
all eyespots refer to a single wikipedia page. Clusters make pretty much no sense at all: what’s the rationale for a “work” cluster.

Some results are completely missing: where is a reference for the Unix tool “tail”???? cf http://en.wikipedia.org/wiki/Tail_(Unix)

pretty disappointing in my eyes(pots)

mark

]]> By: Simeon http://www.searchenginejournal.com/eyeplorer-semantic-search/9244/comment-page-1/#comment-1095993 Simeon Tue, 17 Mar 2009 21:16:28 +0000 http://www.searchenginejournal.com/?p=9244#comment-1095993 Great and nice looking tool. Thank you. Great and nice looking tool. Thank you.

]]>