Show simple item record

dc.contributor.authorMatusov, Evgeny
dc.contributor.authorLeusch, Gregor
dc.contributor.authorFederico, Marcello
dc.contributor.authorMariño Acebal, José Bernardo
dc.contributor.authorNey, Hermann
dc.contributor.authorBertoldi, Nicola
dc.date.accessioned2017-06-15T12:52:19Z
dc.date.issued2008-09-01
dc.identifier.citationMatusov, E., Leusch, G., Federico, M., Mariño, J.B., Ney, H., Bertoldi, N. System combination for machine translation for spoken and written language. "IEEE transactions on audio speech and language processing", 1 Setembre 2008, vol. 16, núm. 7, p. 1222-1237.
dc.identifier.issn1558-7916
dc.identifier.urihttp://hdl.handle.net/2117/105451
dc.description.abstractThis paper describes a recently developed method for computing a consensus translation from the outputs of multiple machine translation (MT) systems. A possibly new translation hypothesis can be produced as a result of this system combination algorithm. The consensus translation is computed by creating a confusion network and performing weighted majority voting, similarly to the well-established ROVER approach of (Fiscus 1997) for combining speech recognition hypotheses. To create the confusion network, pairwise word alignments of the original machine translation hypotheses are learned by using an enhanced statistical alignment algorithm that explicitly models word reordering. This is the first known application of this algorithm in the context of system combination. The context of a whole document of translations rather than a single sentence is taken into account to improve the alignment quality. The proposed alignment and voting approach was evaluated on several machine translation tasks, including a large vocabulary task. The method was also tested in the framework of multi- source and speech translation. Significant improvements in translation quality were achieved on all tasks. Here, we report experimental results for combining MT systems participating in the TC-STAR (speech translation) Project.
dc.format.extent16 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
dc.subject.lcshMachine translating
dc.subject.otherMachine-translation
dc.subject.otherNatural-language
dc.subject.otherSpeech-processing
dc.titleSystem combination for machine translation for spoken and written language
dc.typeArticle
dc.subject.lemacTraducció automàtica
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doi10.1109/TASL.2008.914970
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://www.signalprocessingsociety.org/
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac16676284
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/CE/TC-STAR: Speech-to-speech translation/FP6-IST-506738
dc.date.lift10000-01-01
local.citation.authorMatusov, E.; Leusch, G.; Federico, M.; Mariño, J.B.; Ney, H.; Bertoldi, N.
local.citation.publicationNameIEEE transactions on audio speech and language processing
local.citation.volume16
local.citation.number7
local.citation.startingPage1222
local.citation.endingPage1237


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder