"Multimedia information extraction from HTML product catalogues" . "80-01-03204-3" . "\u010Cesk\u00E9 vysok\u00E9 u\u010Den\u00ED technick\u00E9 v Praze" . "Multimedia information extraction from HTML product catalogues"@en . "Multimedia information extraction from HTML product catalogues"@en . "27240" . . . "Sv\u00E1tek, Vojt\u011Bch" . . . "Desn\u00E1 - \u010Cern\u00E1 \u0158\u00ED\u010Dka" . "Multimedi\u00E1ln\u00ED extrakce informac\u00ED z HTML katalog\u016F produkt\u016F"@cs . . . . . . . . "Dateso 2005" . "P(GA201/03/1318), Z(MSM 311402001)" . "1"^^ . "Information extraction; information retrieval; numerical linear algebra"@en . "V p\u0159\u00EDsp\u011Bvku p\u0159edstavujeme demonstra\u010Dn\u00ED aplikaci extrakce informac\u00ED z internetov\u00FDch str\u00E1nek pr\u016Fmyslov\u00FDch firem, kter\u00E9 nab\u00EDzej\u00ED produkty j\u00EDzdn\u00EDch kol. Pro anal\u00FDzu text\u016F je pou\u017Eit statistick\u00FD p\u0159\u00EDstup (Hidden Markov Models) v kombinaci s r\u016Fzn\u00FDmi metodami klasifikace obr\u00E1zk\u016F, nap\u0159. Latent Semantic Indexing pro anal\u00FDzu obr\u00E1zk\u016F. Pro shlukov\u00E1n\u00ED extrahovan\u00FDch polo\u017Eek do strukturovan\u00FDch objekt\u016F je pou\u017Eita ontologick\u00E1 znalost (Ontological knowledge). V\u00FDsledky jsou ulo\u017Eeny do datov\u00E9ho skladu RDF a jsou p\u0159\u00EDstupn\u00E9 p\u0159es p\u0159eddefinovan\u00E9 dotazovac\u00ED rozhran\u00ED."@cs . "Praha" . "10"^^ . . "Multimedi\u00E1ln\u00ED extrakce informac\u00ED z HTML katalog\u016F produkt\u016F"@cs . "RIV/61989100:27240/05:00013235" . "\u0160v\u00E1b, Ond\u0159ej" . "We describe a demo application of information extraction from company websites, focusing on bicycle product offers. A statistical approach (Hidden Markov Models) is used in combination with different ways of image classification, including latent semantic analysis of image collections. Ontological knowledge is used to group the extracted items into structured objects. The results are stored in an RDF repository and made available for structured search." . . "4"^^ . . "[2E7534433D5C]" . "Multimedia information extraction from HTML product catalogues" . . . . "We describe a demo application of information extraction from company websites, focusing on bicycle product offers. A statistical approach (Hidden Markov Models) is used in combination with different ways of image classification, including latent semantic analysis of image collections. Ontological knowledge is used to group the extracted items into structured objects. The results are stored in an RDF repository and made available for structured search."@en . "531623" . . "Praks, Pavel" . "2005-04-13+02:00"^^ . "RIV/61989100:27240/05:00013235!RIV09-GA0-27240___" . "Labsk\u00FD, Martin" .