Show simple item record

dc.contributor.authorEscolano Peinado, Carlos
dc.contributor.authorRuiz Costa-Jussà, Marta
dc.contributor.authorRodríguez Fonollosa, José Adrián
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.identifier.citationEscolano, C.; Costa-jussà, M.R.; Fonollosa, J.A.R. From bilingual to multilingual neural-based machine translation by incremental training. "Journal of the Association for Information Science and Technology", 2 Agost 2020, vol. 72, núm. 2, p. 190-203.
dc.description.abstractA common intermediate language representation in neural machine translation can be used to extend bilingual systems by incremental training. We propose a new architecture based on introducing an interlingual loss as an additional training objective. By adding and forcing this interlingual loss, we can train multiple encoders and decoders for each language, sharing among them a common intermediate representation. Translation results on the low-resource tasks (Turkish-English and Kazakh-English tasks) show a BLEU improvement of up to 2.8 points. However, results on a larger dataset (Russian-English and Kazakh-English) show BLEU losses of a similar amount. While our system provides improvements only for the low-resource tasks in terms of translation quality, our system is capable of quickly deploying new language pairs without the need to retrain the rest of the system, which may be a game changer in some situations. Specifically, what is most relevant regarding our architecture is that it is capable of: reducing the number of production systems, with respect to the number of languages, from quadratic to linear; incrementally adding a new language to the system without retraining the languages already there; and allowing for translations from the new language to all the others present in the system.
dc.description.sponsorshipThis work also is supported in part by the Google Faculty Research Awards and, also by, the Spanish Ministerio de Economía y Competitividad, the European Regional Development Fund, the Agencia Estatal de Investigación through the postdoctoral senior grant Ramón y Cajal and the projects EUR2019-103819, PCIN-2017-079 andPID2019-107579RB-I00.
dc.format.extent14 p.
dc.rightsAttribution 4.0 International
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshComputational linguistics
dc.subject.lcshMachine translating
dc.subject.otherBilingual systems
dc.subject.otherEncoders and decoders
dc.subject.otherIncremental training
dc.subject.otherIntermediate languages
dc.subject.otherIntermediate representations
dc.titleFrom bilingual to multilingual neural-based machine translation by incremental training
dc.subject.lemacLingüística computacional
dc.subject.lemacTraducció automàtica
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
dc.description.versionPostprint (published version)
local.citation.authorEscolano, C.; Costa-jussà, M. R.; Fonollosa, José A. R.
local.citation.publicationNameJournal of the Association for Information Science and Technology

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 Generic
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution 4.0 Generic