Byte-based neural machine translation
Document typeConference report
PublisherAssociation for Computational Linguistics
Rights accessOpen Access
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.
CitationRuiz, 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.