- -

Improving the minimum description length inference of phrase-based translation models

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Improving the minimum description length inference of phrase-based translation models

Mostrar el registro sencillo del ítem

Ficheros en el ítem

Thumbnail
Nombre: 2015-LNCS-Gonzale ...
Tamaño: 352.5Kb
Formato: PDF
Descripción: Versión del Autor.
Abrir
[Cerrado]
Nombre: 2015-LNCS-Gonzale ...
Tamaño: 256.0Kb
Formato: PDF
Descripción: Versión editorial
Solicitar una copia al autor
dc.contributor.author Gonzalez Rubio, Jesus es_ES
dc.contributor.author Casacuberta Nolla, Francisco es_ES
dc.date.accessioned 2016-05-19T09:31:05Z
dc.date.available 2016-05-19T09:31:05Z
dc.date.issued 2015-06-09
dc.identifier.isbn 978-3-319-19389-2
dc.identifier.issn 0302-9743
dc.identifier.uri http://hdl.handle.net/10251/64367
dc.description The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_25 es_ES
dc.description.abstract We study the application of minimum description length (MDL) inference to estimate pattern recognition models for machine translation. MDL is a theoretically-sound approach whose empirical results are however below those of the state-of-the-art pipeline of training heuristics. We identify potential limitations of current MDL procedures and provide a practical approach to overcome them. Empirical results support the soundness of the proposed approach. es_ES
dc.description.sponsorship Work supported by the EU 7th Framework Programme (FP7/2007–2013) under the CasMaCat project (grant agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014). es_ES
dc.language Inglés es_ES
dc.publisher Springer International Publishing es_ES
dc.relation.ispartof Pattern Recognition and Image Analysis: 7th Iberian Conference, IbPRIA 2015, Santiago de Compostela, Spain, June 17-19, 2015, Proceedings es_ES
dc.relation.ispartofseries Lecture Notes in Computer Science;9117
dc.rights Reserva de todos los derechos es_ES
dc.subject Pattern recognition es_ES
dc.subject.classification LENGUAJES Y SISTEMAS INFORMATICOS es_ES
dc.title Improving the minimum description length inference of phrase-based translation models es_ES
dc.type Capítulo de libro es_ES
dc.identifier.doi 10.1007/978-3-319-19390-8 25
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/287576/EU/Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MINECO//TIN2012-31723/ES/INTERACCION ACTIVA PARA TRANSCRIPCION DE HABLA Y TRADUCCION/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GVA//PROMETEO09%2F2009%2F014/ES/Adaptive learning and multimodality in pattern recognition (Almapater)/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació es_ES
dc.description.bibliographicCitation Gonzalez Rubio, J.; Casacuberta Nolla, F. (2015). Improving the minimum description length inference of phrase-based translation models. En Pattern Recognition and Image Analysis: 7th Iberian Conference, IbPRIA 2015, Santiago de Compostela, Spain, June 17-19, 2015, Proceedings. Springer International Publishing. 219-227. https://doi.org/10.1007/978-3-319-19390-8 25 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion http://link.springer.com/chapter/10.1007/978-3-319-19390-8_25 es_ES
dc.description.upvformatpinicio 219 es_ES
dc.description.upvformatpfin 227 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.relation.senia 290796 es_ES
dc.contributor.funder European Commission es_ES
dc.contributor.funder Ministerio de Ciencia e Innovación es_ES
dc.contributor.funder Generalitat Valenciana es_ES
dc.contributor.funder Ministerio de Economía y Competitividad


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

Mostrar el registro sencillo del ítem