Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair

This work aims to improve an N-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish-Catalan parallel corpus consisting of 1.7 million sentences taken from El Periódico newspaper. Starting from a linguistic error analysis above t...

Descripción completa

Detalles Bibliográficos
Autores: Farrús, Mireia, Costa-jussà, Marta R., Mariño Acebal, José B., Poch, Marc, Hernández, Adolfo, Henríquez, Carlos, Fonollosa, José A Rodriguez
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2011
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/32733
Acceso en línea:http://hdl.handle.net/10230/32733
http://dx.doi.org/10.1007/s10579-011-9137-0
Access Level:acceso abierto
Palabra clave:Statistical machine translation
N-gram-based translation
Linguistic knowledge
Grammatical categories
id ES_bf1b40e0dce5ab02bb9853fa8b32a89b
oai_identifier_str oai:recercat.cat:10230/32733
network_acronym_str ES
network_name_str España
repository_id_str
spelling Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pairFarrús, MireiaCosta-jussà, Marta R.Mariño Acebal, José B.Poch, MarcHernández, AdolfoHenríquez, CarlosFonollosa, José A RodriguezStatistical machine translationN-gram-based translationLinguistic knowledgeGrammatical categoriesThis work aims to improve an N-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish-Catalan parallel corpus consisting of 1.7 million sentences taken from El Periódico newspaper. Starting from a linguistic error analysis above this baseline system, orthographic, morphological, lexical, semantic and syntactic problems are approached using a set of techniques. The proposed solutions include the development and application of additional statistical techniques, text pre- and post-processing tasks, and rules based on the use of grammatical categories, as well as lexical categorization. The performance of the improved system is clearly increased, as is shown in both human and automatic evaluations of the system, with a gain of about 1.1 points BLEU observed in the Spanish-to-Catalan direction of translation, and a gain of about 0.5 points in the reverse direction. The final system is freely available online as a linguistic resource.This work has been partially funded by the Spanish Department of Science and Innovation through the Juan de la Cierva fellowship program and the Spanish Government under the BUCEADOR project (TEC2009-14094-C04-01).Springer201720172011info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/32733http://dx.doi.org/10.1007/s10579-011-9137-0reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésLanguage resources and evaluation. 2011;45(2):181-208.info:eu-repo/grantAgreement/ES/3PN/TEC2009-14094-C04-01© Springer The final publication is available at Springer via http://dx.doi.org/10.1007/s10579-011-9137-0”info:eu-repo/semantics/openAccessoai:recercat.cat:10230/327332026-05-29T05:05:01Z
dc.title.none.fl_str_mv Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
title Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
spellingShingle Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
Farrús, Mireia
Statistical machine translation
N-gram-based translation
Linguistic knowledge
Grammatical categories
title_short Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
title_full Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
title_fullStr Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
title_full_unstemmed Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
title_sort Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
dc.creator.none.fl_str_mv Farrús, Mireia
Costa-jussà, Marta R.
Mariño Acebal, José B.
Poch, Marc
Hernández, Adolfo
Henríquez, Carlos
Fonollosa, José A Rodriguez
author Farrús, Mireia
author_facet Farrús, Mireia
Costa-jussà, Marta R.
Mariño Acebal, José B.
Poch, Marc
Hernández, Adolfo
Henríquez, Carlos
Fonollosa, José A Rodriguez
author_role author
author2 Costa-jussà, Marta R.
Mariño Acebal, José B.
Poch, Marc
Hernández, Adolfo
Henríquez, Carlos
Fonollosa, José A Rodriguez
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Statistical machine translation
N-gram-based translation
Linguistic knowledge
Grammatical categories
topic Statistical machine translation
N-gram-based translation
Linguistic knowledge
Grammatical categories
description This work aims to improve an N-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish-Catalan parallel corpus consisting of 1.7 million sentences taken from El Periódico newspaper. Starting from a linguistic error analysis above this baseline system, orthographic, morphological, lexical, semantic and syntactic problems are approached using a set of techniques. The proposed solutions include the development and application of additional statistical techniques, text pre- and post-processing tasks, and rules based on the use of grammatical categories, as well as lexical categorization. The performance of the improved system is clearly increased, as is shown in both human and automatic evaluations of the system, with a gain of about 1.1 points BLEU observed in the Spanish-to-Catalan direction of translation, and a gain of about 0.5 points in the reverse direction. The final system is freely available online as a linguistic resource.
publishDate 2011
dc.date.none.fl_str_mv 2011
2017
2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/32733
http://dx.doi.org/10.1007/s10579-011-9137-0
url http://hdl.handle.net/10230/32733
http://dx.doi.org/10.1007/s10579-011-9137-0
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Language resources and evaluation. 2011;45(2):181-208.
info:eu-repo/grantAgreement/ES/3PN/TEC2009-14094-C04-01
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418341745033216
score 15,811543

Similares en LA Referencia