From bilingual to multilingual neural-based machine translation by incremental training

A 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 c...

Descripción completa

Detalles Bibliográficos
Autores: Escolano Peinado, Carlos|||0000-0001-6657-673X, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Tipo de recurso: artículo
Fecha de publicación:2020
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/341408
Acceso en línea:https://hdl.handle.net/2117/341408
https://dx.doi.org/10.1002/asi.24395
Access Level:acceso abierto
Palabra clave:Computational linguistics
Machine translating
Architecture-based
Bilingual systems
Encoders and decoders
Incremental training
Intermediate languages
Intermediate representations
Lingüística computacional
Traducció automàtica
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
Descripción
Sumario:A 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.