This HTML5 document contains 47 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n12http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n23http://localhost/temp/predkladatel/
n13http://purl.org/net/nknouf/ns/bibtex#
n11http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n10http://linked.opendata.cz/resource/domain/vavai/projekt/
n20http://linked.opendata.cz/resource/domain/vavai/subjekt/
n19http://linked.opendata.cz/ontology/domain/vavai/
n22http://linked.opendata.cz/resource/domain/vavai/zamer/
n15https://schema.org/
shttp://schema.org/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/
skoshttp://www.w3.org/2004/02/skos/core#
n7http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F11%3A10107931%21RIV12-GA0-11320___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n14http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n9http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n16http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F11%3A10107931%21RIV12-GA0-11320___
rdf:type
skos:Concept n19:Vysledek
dcterms:description
We use target-side monolingual data to extend the vocabulary of the translation model in statistical machine translation. This method called %22reverse self-training%22 improves the decoder's ability to produce grammatically correct translations into languages with morphology richer than the source language esp. in small-data setting. We empirically evaluate the gains for several pairs of European languages and discuss some approaches of the underlying back-off techniques needed to translate unseen forms of known words. We also provide a description of the systems we submitted to WMT11 Shared Task. We use target-side monolingual data to extend the vocabulary of the translation model in statistical machine translation. This method called %22reverse self-training%22 improves the decoder's ability to produce grammatically correct translations into languages with morphology richer than the source language esp. in small-data setting. We empirically evaluate the gains for several pairs of European languages and discuss some approaches of the underlying back-off techniques needed to translate unseen forms of known words. We also provide a description of the systems we submitted to WMT11 Shared Task.
dcterms:title
Improving Translation Model by Monolingual Data Improving Translation Model by Monolingual Data
skos:prefLabel
Improving Translation Model by Monolingual Data Improving Translation Model by Monolingual Data
skos:notation
RIV/00216208:11320/11:10107931!RIV12-GA0-11320___
n19:predkladatel
n20:orjk%3A11320
n4:aktivita
n9:Z n9:P
n4:aktivity
P(7E09003), P(GPP406/10/P259), Z(MSM0021620838)
n4:dodaniDat
n16:2012
n4:domaciTvurceVysledku
n11:3528839 n11:2630176
n4:druhVysledku
n17:D
n4:duvernostUdaju
n8:S
n4:entitaPredkladatele
n7:predkladatel
n4:idSjednocenehoVysledku
203977
n4:idVysledku
RIV/00216208:11320/11:10107931
n4:jazykVysledku
n14:eng
n4:klicovaSlova
data; monolingual; model; translation; improving
n4:klicoveSlovo
n5:model n5:data n5:monolingual n5:translation n5:improving
n4:kontrolniKodProRIV
[BA905E93FDCD]
n4:mistoKonaniAkce
Edinburgh, United Kingdom
n4:mistoVydani
Edinburgh, UK
n4:nazevZdroje
Proceedings of the Sixth Workshop on Statistical Machine Translation
n4:obor
n18:AI
n4:pocetDomacichTvurcuVysledku
2
n4:pocetTvurcuVysledku
2
n4:projekt
n10:GPP406%2F10%2FP259 n10:7E09003
n4:rokUplatneniVysledku
n16:2011
n4:tvurceVysledku
Tamchyna, Aleš Bojar, Ondřej
n4:typAkce
n12:CST
n4:zahajeniAkce
2011-07-30+02:00
n4:zamer
n22:MSM0021620838
s:numberOfPages
7
n13:hasPublisher
Association for Computational Linguistics
n15:isbn
978-1-937284-12-1
n23:organizacniJednotka
11320