This HTML5 document contains 49 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n21http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n18http://localhost/temp/predkladatel/
n15http://purl.org/net/nknouf/ns/bibtex#
n14http://linked.opendata.cz/resource/domain/vavai/projekt/
n7http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n10http://linked.opendata.cz/ontology/domain/vavai/
n22https://schema.org/
n16http://linked.opendata.cz/resource/domain/vavai/zamer/
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/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F09%3A10077993%21RIV11-MSM-11320___/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n12http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n9http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n17http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F09%3A10077993%21RIV11-MSM-11320___
rdf:type
skos:Concept n10:Vysledek
dcterms:description
We would like to draw attention to Hidden Markov Tree Models (HMTM), which are to our knowledge still unexploited in the field of Computational Linguistics, in spite of highly successful Hidden Markov (Chain) Models. In dependency trees, the independence assumptions made by HMTM correspond to the intuition of linguistic dependency. Therefore we suggest to use HMTM and tree-modified Viterbi algorithm for tasks interpretable as labeling nodes of dependency trees. In particular, we show that the transfer phase in a Machine Translation system based on tectogrammatical dependency trees can be seen as a task suitable for HMTM. When using the HMTM approach for the English-Czech translation, we reach a moderate improvement over the baseline. We would like to draw attention to Hidden Markov Tree Models (HMTM), which are to our knowledge still unexploited in the field of Computational Linguistics, in spite of highly successful Hidden Markov (Chain) Models. In dependency trees, the independence assumptions made by HMTM correspond to the intuition of linguistic dependency. Therefore we suggest to use HMTM and tree-modified Viterbi algorithm for tasks interpretable as labeling nodes of dependency trees. In particular, we show that the transfer phase in a Machine Translation system based on tectogrammatical dependency trees can be seen as a task suitable for HMTM. When using the HMTM approach for the English-Czech translation, we reach a moderate improvement over the baseline.
dcterms:title
Hidden Markov Tree Model in Dependency-based Machine Translation Hidden Markov Tree Model in Dependency-based Machine Translation
skos:prefLabel
Hidden Markov Tree Model in Dependency-based Machine Translation Hidden Markov Tree Model in Dependency-based Machine Translation
skos:notation
RIV/00216208:11320/09:10077993!RIV11-MSM-11320___
n3:aktivita
n12:Z n12:P
n3:aktivity
P(1ET101120503), P(LC536), Z(MSM0021620838)
n3:dodaniDat
n17:2011
n3:domaciTvurceVysledku
n7:4217888 n7:3450058
n3:druhVysledku
n9:D
n3:duvernostUdaju
n13:S
n3:entitaPredkladatele
n11:predkladatel
n3:idSjednocenehoVysledku
317072
n3:idVysledku
RIV/00216208:11320/09:10077993
n3:jazykVysledku
n8:eng
n3:klicovaSlova
translation; machine; based; dependency; model; tree; markov; hidden
n3:klicoveSlovo
n4:translation n4:model n4:tree n4:hidden n4:dependency n4:markov n4:based n4:machine
n3:kontrolniKodProRIV
[A524DFC0D8F4]
n3:mistoKonaniAkce
Suntec, Singapore
n3:mistoVydani
Suntec, Singapore
n3:nazevZdroje
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
n3:obor
n19:AI
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n14:LC536 n14:1ET101120503
n3:rokUplatneniVysledku
n17:2009
n3:tvurceVysledku
Žabokrtský, Zdeněk Popel, Martin
n3:typAkce
n21:WRD
n3:zahajeniAkce
2009-08-02+02:00
n3:zamer
n16:MSM0021620838
s:numberOfPages
4
n15:hasPublisher
Association for Computational Linguistics
n22:isbn
978-1-932432-61-9
n18:organizacniJednotka
11320