Augmenting Neural Machine Translation through Round-Trip Training Approach
Open Computer Science · 01.01.2019 · 9 (1) · 268-278
DOI: 10.1515/comp-2019-0019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Open Computer Science, online erschienen am 11.10.2019. Verfasst von Benyamin Ahmadnia und 1 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally, the NMT systems learn from millions of words from bilingual training dataset. However, human labeling process is very costly and time consuming. In this paper, we describe a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data bottleneck, thus augmenting translation quality. We conduct detailed experiments on English-Spanish as a high-resource language pair as well as Persian-Spanish as a low-resource language pair. Experimental results show that this competitive approach outperforms the baseline systems and improves translation quality.
Zitieren
APA
Ahmadnia, B., & Dorr, B. J. (2019). Augmenting Neural Machine Translation through Round-Trip Training Approach. Open Computer Science, 9(1), 268-278. https://doi.org/10.1515/comp-2019-0019
Vancouver
Ahmadnia B, Dorr BJ. Augmenting Neural Machine Translation through Round-Trip Training Approach. Open Computer Science. 2019;9(1):268-278. doi:10.1515/comp-2019-0019
BibTeX
@article{Ahmadnia2019,
author = {Ahmadnia, Benyamin and Dorr, Bonnie J.},
title = {Augmenting Neural Machine Translation through Round-Trip Training Approach},
journal = {Open Computer Science},
year = {2019},
volume = {9},
number = {1},
pages = {268--278},
doi = {10.1515/comp-2019-0019}
}
EUVIMED