. . . "RIV/49777513:23520/06:00000237!RIV07-MSM-23520___" . "0302-9743" . . . "Jur\u010D\u00ED\u010Dek, Filip" . "23520" . "RIV/49777513:23520/06:00000237" . "4"^^ . . . "Use of Negative Examples in Training the HVS Semantic Model" . "[C8F268E2A4CF]" . "8"^^ . . "505301" . . . "4"^^ . "Jel\u00EDnek, Libor" . "DE - Spolkov\u00E1 republika N\u011Bmecko" . . "0" . "Use of Negative Examples in Training the HVS Semantic Model" . "Zahradil, Ji\u0159\u00ED" . "This paper describes use of negative examples in training the HVS semantic model. We present a novel initialization of the lexical model using negative examples extracted automatically from a semantic corpus as well as description of an algorithm for extraction these examples. We evaluated the use of negative examples on a closed domain human-human train timetable dialogue corpus. We significantly improved the standard PARSEVAL scores of the baseline system. The labeled F-measure (LF) was increased from 45.4% to 49.1%."@en . . "semantic model, HVS, negative examples, train timetable corpus"@en . . "Vliv negativn\u00EDch p\u0159\u00EDklad\u016F na tr\u00E9nov\u00E1n\u00ED HVS s\u00E9mantick\u00E9ho modelu"@cs . . "605" . . "This paper describes use of negative examples in training the HVS semantic model. We present a novel initialization of the lexical model using negative examples extracted automatically from a semantic corpus as well as description of an algorithm for extraction these examples. We evaluated the use of negative examples on a closed domain human-human train timetable dialogue corpus. We significantly improved the standard PARSEVAL scores of the baseline system. The labeled F-measure (LF) was increased from 45.4% to 49.1%." . . . "\u0160vec, Jan" . "P(1M0567)" . "\u010Cl\u00E1nek popisuje HVS s\u00E9mantick\u00FD model a nov\u00FD zp\u016Fsob zlep\u0161en\u00ED \u00FA\u010Den\u00ED modelu n a z\u00E1klad\u011B negativn\u00EDch p\u0159\u00EDklad\u016F extrahovan\u00FDch (automaticky) z ru\u010Dn\u011B anotovan\u00E9ho korpusu. Korpus je souhrn dialog\u016F z uzav\u0159en\u00E9 \u00FAlohy vlakov\u00FDch dotaz\u016F. Standardn\u00ED PARSEVAL sk\u00F3re z\u00E1kladn\u00EDho syst\u00E9mu se v\u00FDznamn\u011B zlep\u0161ilo. F-measure (LF) se zv\u00FD\u0161ilo z 45.4% na 49.1%."@cs . "Vliv negativn\u00EDch p\u0159\u00EDklad\u016F na tr\u00E9nov\u00E1n\u00ED HVS s\u00E9mantick\u00E9ho modelu"@cs . "Use of Negative Examples in Training the HVS Semantic Model"@en . . "Lecture Notes in Artificial Intelligence" . "Use of Negative Examples in Training the HVS Semantic Model"@en . .