This HTML5 document contains 45 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n4http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n17http://localhost/temp/predkladatel/
n5http://purl.org/net/nknouf/ns/bibtex#
n16http://linked.opendata.cz/resource/domain/vavai/projekt/
n9http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n19http://linked.opendata.cz/ontology/domain/vavai/
n18https://schema.org/
n10http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F49777513%3A23520%2F08%3A00500817%21RIV10-MSM-23520___/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n11http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n12http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n7http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F49777513%3A23520%2F08%3A00500817%21RIV10-MSM-23520___
rdf:type
skos:Concept n19:Vysledek
dcterms:description
The hidden vector state (HVS) parser is a popular method for semantic parsing. It is used in the language understanding module of the statistical based spoken dialog system. This paper presents an extension of the HVS semantic parser. It enables the parser to generate broader class of semantic trees. This modication can be used to improve the performance of the parser by generating not only the right-branching trees (like original HVS parser) but also limited left-branching trees and their combinations. The extension retains simplicity and properties of the original HVS parser. We tested the method on Czech human-human train timetable corpus. The modied HVS parser yields statistically signicant improvement. The accuracy of the system increased from 50.4% to 58.3% absolutely. The hidden vector state (HVS) parser is a popular method for semantic parsing. It is used in the language understanding module of the statistical based spoken dialog system. This paper presents an extension of the HVS semantic parser. It enables the parser to generate broader class of semantic trees. This modication can be used to improve the performance of the parser by generating not only the right-branching trees (like original HVS parser) but also limited left-branching trees and their combinations. The extension retains simplicity and properties of the original HVS parser. We tested the method on Czech human-human train timetable corpus. The modied HVS parser yields statistically signicant improvement. The accuracy of the system increased from 50.4% to 58.3% absolutely.
dcterms:title
Extension of HVS semantic parser by allowing left-right branching Extension of HVS semantic parser by allowing left-right branching
skos:prefLabel
Extension of HVS semantic parser by allowing left-right branching Extension of HVS semantic parser by allowing left-right branching
skos:notation
RIV/49777513:23520/08:00500817!RIV10-MSM-23520___
n3:aktivita
n8:P
n3:aktivity
P(1M0567), P(LC536)
n3:dodaniDat
n7:2010
n3:domaciTvurceVysledku
n9:5077508 n9:8780943 n9:6895972
n3:druhVysledku
n14:D
n3:duvernostUdaju
n20:S
n3:entitaPredkladatele
n10:predkladatel
n3:idSjednocenehoVysledku
367455
n3:idVysledku
RIV/49777513:23520/08:00500817
n3:jazykVysledku
n12:eng
n3:klicovaSlova
semantic analysis; spoken dialogue systems; spoken language understanding
n3:klicoveSlovo
n11:spoken%20dialogue%20systems n11:semantic%20analysis n11:spoken%20language%20understanding
n3:kontrolniKodProRIV
[B7F45E9A69A8]
n3:mistoKonaniAkce
Las Vegas, Nevada, U.S.A.
n3:mistoVydani
New York
n3:nazevZdroje
2008 IEEE International Conference on Acoustics, Speech, and Signal Processing
n3:obor
n13:JD
n3:pocetDomacichTvurcuVysledku
3
n3:pocetTvurcuVysledku
3
n3:projekt
n16:1M0567 n16:LC536
n3:rokUplatneniVysledku
n7:2008
n3:tvurceVysledku
Müller, Luděk Švec, Jan Jurčíček, Filip
n3:typAkce
n4:WRD
n3:wos
000257456703232
n3:zahajeniAkce
2008-04-04+02:00
s:numberOfPages
4
n5:hasPublisher
IEEE
n18:isbn
978-1-4244-1483-3
n17:organizacniJednotka
23520