EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages

G. M. Harshitha, Vasudeva, Nisha P. Poojary, P. Kamakshi Bhat

Engineering, Technology & Applied Science Research · 11.08.2026 · 16 (4) · 38213-38220

DOI: 10.48084/etasr.18415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 11.08.2026. Verfasst von G. M. Harshitha und 3 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-resource languages face significant challenges in Machine Translation (MT) due to the scarcity of high-quality parallel datasets. This study presents a low-resource language translation system using a multilingual Neural Machine Translation (NMT) approach. The proposed system employs the Multilingual Bidirectional and Auto-Regressive Transformer-50 (mBART-50) model. mBART-50 is a transformer-based multilingual architecture, fine-tuned on the Samanantar dataset to enhance translation quality for Indic languages. English–Tamil and English–Telugu translations are the primary experimental focus, in which cross-lingual transfer learning is leveraged to improve performance despite data scarcity. Model performance is evaluated using the Bilingual Evaluation Understudy (BLEU) score, which demonstrates an improvement over the pretrained baseline model. The mBART-50 is designed to be multilingual to enable its easy generalization to other low-resource Indic languages. This study extends previous research by assessing the effectiveness of multilingual transfer under the low-resource conditions of Indic languages. The fine-tuned model achieves BLEU scores of 45.91 for English–Tamil and 31.23 for English–Telugu, significantly outperforming the pretrained baseline. These results demonstrate the effectiveness of multilingual transfer learning in low-resource settings.

Zitieren

APA

Harshitha, G. M., Vasudeva, Poojary, N. P., & Bhat, P. K. (2026). A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages. Engineering, Technology & Applied Science Research, 16(4), 38213-38220. https://doi.org/10.48084/etasr.18415

Vancouver

Harshitha GM, Vasudeva, Poojary NP, Bhat PK. A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages. Engineering, Technology & Applied Science Research. 2026;16(4):38213-38220. doi:10.48084/etasr.18415

BibTeX
@article{Harshitha2026,
  author = {Harshitha, G. M. and Vasudeva and Poojary, Nisha P. and Bhat, P. Kamakshi},
  title = {A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {38213--38220},
  doi = {10.48084/etasr.18415}
}
Kostenlos starten →