" fulltext search" . "information systems" . . " morphological analysis" . . "The project %22Resources and Tools for Information Systems%22 focuses on fulltext information systems (containing both written and spoken materials) in Czech (where standard methods fail due to the different type of languages they have been developed for). The project aims to strenghten and improve current methods for morphological analysis of Czech, in order to attain higher precison in identifying lexical units and in some cases also their meaning. The project will use state-of-the-art statistical technology and machine learning based on linguistically annotated data. Within the project, such data will be prepared (at a fraction of the usual cost) by conversion of older resources, and tools will be created (based on the resulting larger corpus) that would have parameters needed for a successful application in end-user information systems."@en . "1"^^ . . "2009-05-04+02:00"^^ . "42"^^ . "0"^^ . "42"^^ . "Projekt aplikovan\u00E9ho v\u00FDzkumu %22Datov\u00E9 zdroje a n\u00E1stroje pro informa\u010Dn\u00ED syst\u00E9my%22 \u0159e\u0161\u00ED problematiku c\u00EDlen\u00E9ho vyhled\u00E1v\u00E1n\u00ED ve fulltextov\u00FDch syst\u00E9mech (psan\u00FDch \u010Di mluven\u00FDch) v \u010De\u0161tin\u011B (kde pou\u017Eit\u00ED standardn\u00EDch technologick\u00FDch postup\u016F vyvinut\u00FDch pro jazyky jin\u00E9ho typu poskytuje v\u00FDrazn\u011B hor\u0161\u00ED v\u00FDsledky a komfort pro u\u017Eivatele). J\u00E1drem projektu je pos\u00EDlen\u00ED sou\u010Dasn\u00FDch metod automatick\u00E9 morfologick\u00E9 (tvaroslovn\u00E9) anal\u00FDzy \u010De\u0161tiny sm\u011Brem k vy\u0161\u0161\u00ED p\u0159esnosti identifikace lexik\u00E1ln\u00EDch jednotek a \u010D\u00E1ste\u010Dn\u011B i jejich v\u00FDznam\u016F. Projekt vyu\u017Eije dne\u0161n\u00ED \u0161pi\u010Dkov\u00E9 sv\u011Btov\u00E9 technologie, kter\u00E9 jsou zalo\u017Eeny na statistick\u00FDch metod\u00E1ch a strojov\u00E9m u\u010Den\u00ED na z\u00E1klad\u011B lingvisticky anotovan\u00FDch dat. Pro tyto \u00FA\u010Dely budou v projektu p\u0159ipravena anotovan\u00E1 data (za v\u00FDrazn\u011B ni\u017E\u0161\u00EDch n\u00E1klad\u016F ne\u017E v minulosti, pomoc\u00ED automatick\u00E9 konverze ze star\u0161\u00EDch zdroj\u016F), slou\u010Dena s existuj\u00EDc\u00EDcmi daty a na jejich z\u00E1klad\u011B vytvo\u0159eny n\u00E1stroje pro morfologickou anal\u00FDzu be\u017En\u00E9ho textu s takov\u00FDmi parametry, kter\u00E9 budou umo\u017E\u0148ovat nasazen\u00ED v praxi." . . . "2"^^ . . . " human-machine communication (in Czech)" . "Data a n\u00E1stroje pro informa\u010Dn\u00ED syst\u00E9my" . . . "information systems; fulltext search; question-answering systems; human-machine communication (in Czech); morphological analysis; tagging; annotated corpora"@en . "2004-07-01+02:00"^^ . "1ET101120413" . . . "We built an extensive data base and a pool of natural language tools: The Czech Academic Corpus, The Reference Dictionary of Czech, The Kott\u00B4s dictionary and The Jungmann\u00B4s dictionary; tools for morphological and syntactic processing of Czech."@en . . "2008-12-31+01:00"^^ . . "Resources and Tools for Information Systems"@en . "2008-02-21+01:00"^^ . " question-answering systems" . . . . "Vytvo\u0159en\u00ED rozs\u00E1hl\u00E9 z\u00E1kladny jazykov\u00FDch dat a n\u00E1stroj\u016F: \u010Cesk\u00FD akademick\u00FD korpus, P\u0159\u00EDru\u010Dn\u00ED slovn\u00EDk jazyka \u010Desk\u00E9ho, Kott\u016Fv slovn\u00EDk a Jungmann\u016Fv slovn\u00EDk; n\u00E1stroje pro morfologick\u00E9 a syntaktick\u00E9 zpracov\u00E1n\u00ED \u010Desk\u00FDch text\u016F."@cs . "http://www.isvav.cz/projectDetail.do?rowId=1ET101120413"^^ . . . " tagging" . . .