2026-04-13T05:58:08Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/1148772025-07-17T03:03:39Zcom_2072_1033col_2072_452950

Byte-based neural machine translation Ruiz Costa-Jussà, Marta Escolano Peinado, Carlos Rodríguez Fonollosa, José Adrián Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla Àrees temàtiques de la UPC::Informàtica Neural Networks (Computer) Neural Machine Translation Deep Learning Tractament del llenguatge natural (Informàtica) Xarxes neuronals (Informàtica) This paper presents experiments compar- ing character-based and byte-based neural machine translation systems. The main motivation of the byte-based neural ma- chine translation system is to build multi- lingual neural machine translation systems that can share the same vocabulary. We compare the performance of both systems in several language pairs and we see that the performance in test is similar for most language pairs while the training time is slightly reduced in the case of byte-based neural machine translation. Postprint (author's final draft) 2017 Conference report Ruiz, M., Escolano, C., Fonollosa, J. A. R. Byte-based neural machine translation. A: Conference on Empirical Methods in Natural Language Processing. "Proceedings of the First Workshop on Subword and Character Level Models in NLP". Stroudsburg, PA: Association for Computational Linguistics, 2017, p. 154-158. 978-1-945626-91-3 https://hdl.handle.net/2117/114877 eng http://www.aclweb.org/anthology/W/W17/W17-4123.pdf info:eu-repo/grantAgreement/MINECO//TEC2015-69266-P/ES/TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO/ http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Open Access Attribution-NonCommercial-NoDerivs 3.0 Spain 5 p. application/pdf Association for Computational Linguistics