Show simple item record

dc.contributor.advisorAranberri Monasterio, Nora
dc.contributor.authorDe Gibert Bonet, Ona
dc.date.accessioned2018-07-03T08:35:28Z
dc.date.available2018-07-03T08:35:28Z
dc.date.issued2018
dc.date.submitted2018-06
dc.identifier.urihttp://hdl.handle.net/10810/27864
dc.description.abstract[EN]The implementation of a machine translation system into production is not enough to warrant its efficient use. There exists the need to know when it is profitable to use machine translation as opposed to translating from scratch. That is why being able to estimate the quality of a machine translation is crucial. This thesis investigates the task of quality estimation of machine translation for a specific machine translation system and a specific domain by developing a recommender system for Spanish to English. The work further investigates how quality estimation can benefit from the use of linguistic characteristics in contrast to the more common shallower features. The data was collected from real translators who performed a post-editing task, and the linguistic features were manually annotated. First, we build a classification model that selects sentences for post-editing or translating. Secondly, we perform a regression task based on three quality indicators: Quality, Time and HTER. Although experimentation shows some promising results, overall the selected features are not discriminative enough for the recommender system to be implemented into production. Results are discussed at different levels, suggesting a replication at a larger scale, with automatic annotation of informative linguistic features.es_ES
dc.description.abstract[EU]Itzulpen automatikoko sistema bat produkzio-katean sartzeak ez du bere horretan erabilera eraginkor bat bermatzen. Beharrezkoa da jakitea noiz den probetxugarria itzulpen automatikoa editatzea eta noiz eskuz itzultzea. Horretarako ezinbestekoa da itzulpen automatikoaren kalitatea aurreikusteko gai izatea. Lan honek ikertzen du itzulpen automatikoaren kalitatearen estimazioa sistema zehatz batentzat eta domeinu zehatz baterako, gomendio sistema bat garatuz gaztelaniatik ingelesera itzultzerakoan erabiltzeko. Lanean aztertzen da nola lagundu dezaketen ezaugarri linguistikoek kalitatearen estimazioan, ohikoak diren azaleko ezaugarriekin alderatuta. Datuak itzultzaile profesionalen postedizio lanetik bildu dira eta ezaugarri linguistikoak eskuz etiketatu. Lehenengo, esaldi bat posteditatzea edo itzultzea gomendatzen duten sailkapen ereduak eraiki dira. Bigarrenik, erregresio ereduak entrenatu dira hiru kalitate adierazle aurreikusteko: kalitatea, denbora eta HTER. Esperimentuek emaitza adierazgarriak erakusten dituzten arren, orokorrean erabilitako ezaugarriek ez dute behar bezala bereizten edizio mota komenigarriena zein den, eta beraz, gomendio sistemaren doitasuna ez da produkzioan ezartzeko nahikoa. Emaitzak maila desberdinetan aztertu dira eta esperimentazioa datu-multzo zabalago batekin egitea proposatzen da, anotazio automatikoa erabilita eta informatiboagoak diren ezaugarri linguistikoak erabilita.es_ES
dc.language.isoenges_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/*
dc.subjectlinguistic featureses_ES
dc.subjectmachine translationes_ES
dc.subjectpost-editinges_ES
dc.subjectquality estimationes_ES
dc.subjectrecommender systemes_ES
dc.subjectezaugarri linguistikoakes_ES
dc.subjectitzulpen automatikoaes_ES
dc.subjectpostedizioaes_ES
dc.subjectkalitatearen estimazioaes_ES
dc.subjectgomendio-sistemaes_ES
dc.titleto post-edit or to translate ... That is the question: a case study of a recommender system for Quality Estimation of Machine Translation based on linguistic featureses_ES
dc.typeinfo:eu-repo/semantics/masterThesises_ES
dc.rights.holderAtribución-NoComercial-CompartirIgual 3.0 España*
dc.departamentoesLenguajes y sistemas informáticoses_ES
dc.departamentoeuHizkuntza eta sistema informatikoakes_ES


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Atribución-NoComercial-CompartirIgual 3.0 España
Except where otherwise noted, this item's license is described as Atribución-NoComercial-CompartirIgual 3.0 España