EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data

Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh, Grigori Sidorov

Applied Sciences · 16.01.2023 · 13 (2) · 1201

DOI: 10.3390/app13021201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.01.2023. Verfasst von Atnafu Lambebo Tonja und 3 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mexican Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the many proposals to solve the neural machine translation (NMT) problem of low-resource languages, it continues to be difficult. The issue becomes even more complicated when few resources cover only a single domain. In this paper, we discuss the applicability of a source-side monolingual dataset of low-resource languages to improve the NMT system for such languages. In our experiments, we used Wolaytta–English translation as a low-resource language. We discuss the use of self-learning and fine-tuning approaches to improve the NMT system for Wolaytta–English translation using both authentic and synthetic datasets. The self-learning approach showed +2.7 and +2.4 BLEU score improvements for Wolaytta–English and English–Wolaytta translations, respectively, over the best-performing baseline model. Further fine-tuning the best-performing self-learning model showed +1.2 and +0.6 BLEU score improvements for Wolaytta–English and English–Wolaytta translations, respectively. We reflect on our contributions and plan for the future of this difficult field of study.

Förderung

  • Mexican Government

Zitieren

APA

Tonja, A. L., Kolesnikova, O., Gelbukh, A., & Sidorov, G. (2023). Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data. Applied Sciences, 13(2), 1201. https://doi.org/10.3390/app13021201

Vancouver

Tonja AL, Kolesnikova O, Gelbukh A, Sidorov G. Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data. Applied Sciences. 2023;13(2):1201. doi:10.3390/app13021201

BibTeX
@article{Tonja2023,
  author = {Tonja, Atnafu Lambebo and Kolesnikova, Olga and Gelbukh, Alexander and Sidorov, Grigori},
  title = {Low-Resource Neural Machine Translation Improvement Using Source-Side Monolingual Data},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {2},
  pages = {1201},
  doi = {10.3390/app13021201}
}
Kostenlos starten →