- -

A Deep Source-Context Feature for Lexical Selection in Statistical Machine Translation

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

A Deep Source-Context Feature for Lexical Selection in Statistical Machine Translation

Mostrar el registro sencillo del ítem

Ficheros en el ítem

Thumbnail
Nombre: PRL-autor.pdf
Tamaño: 381.3Kb
Formato: PDF
Descripción: Versión del Autor.
Abrir
[Cerrado]
Nombre: PatternRecognitio ...
Tamaño: 746.9Kb
Formato: PDF
Descripción: Versión editorial
Solicitar una copia al autor
dc.contributor.author Gupta, Parth Alokkumar es_ES
dc.contributor.author Costa-Jussa, Marta R es_ES
dc.contributor.author Rosso, Paolo es_ES
dc.contributor.author Banchs, Rafael es_ES
dc.date.accessioned 2017-06-09T11:41:11Z
dc.date.available 2017-06-09T11:41:11Z
dc.date.issued 2016-05
dc.identifier.issn 0167-8655
dc.identifier.uri http://hdl.handle.net/10251/82653
dc.description this is the author’s version of a work that was accepted for publication in Pattern Recognition Letters . Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Pattern Recognition Letters 75 (2016) 24–29. DOI 10.1016/j.patrec.2016.02.014. es_ES
dc.description.abstract This paper presents a methodology to address lexical disambiguation in a standard phrase-based statistical machine translation system. Similarity among source contexts is used to select appropriate translation units. The information is introduced as a novel feature of the phrase-based model and it is used to select the translation units extracted from the training sentence more similar to the sentence to translate. The similarity is computed through a deep autoencoder representation, which allows to obtain effective lowdimensional embedding of data and statistically significant BLEU score improvements on two different tasks (English-to-Spanish and English-to-Hindi). © 2016 Elsevier B.V. All rights reserved. es_ES
dc.description.sponsorship The work of the first author has been supported by FPI UPV pre-doctoral grant (num. registro - 3505). The work of the second author has been supported by Spanish Ministerio de Economia y Competitividad, contract TEC2015-69266-P and the Seventh Framework Program of the European Commission through the International Outgoing Fellowship Marie Curie Action (IMTraP-2011-29951). The work of the third author has been supported by the Spanish Ministerio de Economia y Competitividad, SomEMBED TIN2015-71147-C2-1-P research project and by the Generalitat Valenciana under the grant ALMAPATER (PrometeoII/2014/030). en_EN
dc.language Inglés es_ES
dc.publisher Elsevier es_ES
dc.relation.ispartof Pattern Recognition Letters es_ES
dc.rights Reserva de todos los derechos es_ES
dc.subject Natural language processing es_ES
dc.subject Neural nets and related approaches es_ES
dc.subject Semantics es_ES
dc.subject.classification LENGUAJES Y SISTEMAS INFORMATICOS es_ES
dc.title A Deep Source-Context Feature for Lexical Selection in Statistical Machine Translation es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1016/j.patrec.2016.02.014
dc.relation.projectID info:eu-repo/grantAgreement/MINECO//TEC2015-69266-P/ES/TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/29951/EU/International Outgoing Fellowship Marie Curie Action es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MINECO//TIN2015-71147-C2-1-P/ES/COMPRENSION DEL LENGUAJE EN LOS MEDIOS DE COMUNICACION SOCIAL - REPRESENTANDO CONTEXTOS DE FORMA CONTINUA/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GVA//PROMETEOII%2F2014%2F030/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escola Tècnica Superior d'Enginyeria Informàtica es_ES
dc.description.bibliographicCitation Gupta, PA.; Costa-Jussa, MR.; Rosso, P.; Banchs, R. (2016). A Deep Source-Context Feature for Lexical Selection in Statistical Machine Translation. Pattern Recognition Letters. 75:24-29. https://doi.org/10.1016/j.patrec.2016.02.014 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion http://dx.doi.org/10.1016/j.patrec.2016.02.014 es_ES
dc.description.upvformatpinicio 24 es_ES
dc.description.upvformatpfin 29 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 75 es_ES
dc.relation.senia 326669 es_ES
dc.contributor.funder Generalitat Valenciana es_ES
dc.contributor.funder Ministerio de Economía y Competitividad
dc.contributor.funder European Commission


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem