This HTML5 document contains 44 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n9http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n20http://localhost/temp/predkladatel/
n10http://purl.org/net/nknouf/ns/bibtex#
n7http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n8http://linked.opendata.cz/ontology/domain/vavai/
n17https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n4http://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#
n14http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F14%3A10289361%21RIV15-MSM-11320___/
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n16http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n11http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n12http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n15http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F14%3A10289361%21RIV15-MSM-11320___
rdf:type
skos:Concept n8:Vysledek
dcterms:description
We present a method for improving machine translation (MT) evaluation by targeted paraphrasing of reference sentences. For this purpose, we employ MT systems themselves and adapt them for translating within a single language. We describe this attempt on two types of MT systems -- phrase-based and rule-based. Initially, we experiment with the freely available SMT system Moses. We create translation models from two available sources of Czech paraphrases -- Czech WordNet and the Meteor Paraphrase tables. We extended Moses by a new feature that makes the translation targeted. However, the results of this method are inconclusive. In the view of errors appearing in the new paraphrased sentences, we propose another solution -- targeted paraphrasing using parts of a rule-based translation system included in the NLP framework Treex. We present a method for improving machine translation (MT) evaluation by targeted paraphrasing of reference sentences. For this purpose, we employ MT systems themselves and adapt them for translating within a single language. We describe this attempt on two types of MT systems -- phrase-based and rule-based. Initially, we experiment with the freely available SMT system Moses. We create translation models from two available sources of Czech paraphrases -- Czech WordNet and the Meteor Paraphrase tables. We extended Moses by a new feature that makes the translation targeted. However, the results of this method are inconclusive. In the view of errors appearing in the new paraphrased sentences, we propose another solution -- targeted paraphrasing using parts of a rule-based translation system included in the NLP framework Treex.
dcterms:title
Machine Translation within One Language as a Paraphrasing Technique Machine Translation within One Language as a Paraphrasing Technique
skos:prefLabel
Machine Translation within One Language as a Paraphrasing Technique Machine Translation within One Language as a Paraphrasing Technique
skos:notation
RIV/00216208:11320/14:10289361!RIV15-MSM-11320___
n4:aktivita
n16:S
n4:aktivity
S
n4:dodaniDat
n15:2015
n4:domaciTvurceVysledku
n7:3166732 n7:3528839
n4:druhVysledku
n12:D
n4:duvernostUdaju
n19:S
n4:entitaPredkladatele
n14:predkladatel
n4:idSjednocenehoVysledku
26815
n4:idVysledku
RIV/00216208:11320/14:10289361
n4:jazykVysledku
n11:eng
n4:klicovaSlova
technique; paraphrasing; language; within; translation; machine
n4:klicoveSlovo
n5:machine n5:within n5:technique n5:paraphrasing n5:translation n5:language
n4:kontrolniKodProRIV
[735E82C4A0C7]
n4:mistoKonaniAkce
Demänovská Dolina, Slovakia
n4:mistoVydani
Praha, Czechia
n4:nazevZdroje
Proceedings of the 14th conference ITAT 2014
n4:obor
n18:IN
n4:pocetDomacichTvurcuVysledku
2
n4:pocetTvurcuVysledku
2
n4:rokUplatneniVysledku
n15:2014
n4:tvurceVysledku
Barančíková, Petra Tamchyna, Aleš
n4:typAkce
n9:CST
n4:zahajeniAkce
2014-09-25+02:00
s:issn
1613-0073
s:numberOfPages
6
n10:hasPublisher
Ústav informatiky AV ČR
n17:isbn
978-80-87136-18-8
n20:organizacniJednotka
11320