Multi-Domain Neural Machine Translation

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/76088
Full metadata record
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTars, Sander-
dc.contributor.authorFishel, Mark-
dc.date.accessioned2018-05-31T10:11:12Z-
dc.date.available2018-05-31T10:11:12Z-
dc.date.issued2018-
dc.identifier.citationTars, Sander; Fishel, Mark. “Multi-Domain Neural Machine Translation”. In: Pérez-Ortiz, Juan Antonio, et al. (Eds.). Proceedings of the 21st Annual Conference of the European Association for Machine Translation: 28-30 May 2018, Universitat d'Alacant, Alacant, Spain, pp. 259-268es_ES
dc.identifier.isbn978-84-09-01901-4-
dc.identifier.urihttp://hdl.handle.net/10045/76088-
dc.description.abstractWe present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use multilingual NMT methods to create multi-domain translation systems; we show that this approach results in significant translation quality gains over fine-tuning. We also explore whether the knowledge of pre-specified text domains is necessary; turns out that it is after all, but also that when it is not known quite high translation quality can be reached, and even higher than with known domains in some cases.es_ES
dc.description.sponsorshipThis work was supported by the Estonian Research Council grant no. 1226.es_ES
dc.languageenges_ES
dc.publisherEuropean Association for Machine Translationes_ES
dc.rights© 2018 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CC-BY-ND.es_ES
dc.subjectMachine Translationes_ES
dc.subject.otherLenguajes y Sistemas Informáticoses_ES
dc.titleMulti-Domain Neural Machine Translationes_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.peerreviewedsies_ES
dc.relation.publisherversionhttp://eamt2018.dlsi.ua.es/proceedings-eamt2018.pdfes_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES
Appears in Collections:Congresos - EAMT2018 - Proceedings

Files in This Item:
Files in This Item:
File Description SizeFormat 
ThumbnailEAMT2018-Proceedings_28.pdf1,54 MBAdobe PDFOpen Preview


This item is licensed under a Creative Commons License Creative Commons