EUVIMEDEUVIMED entdecken
Crossref

From Shloka to Shabda: Low-Resource Sanskrit to Bengali Translation

Koushik Biswas, Rupu Ghosh, Mahir Mahbub, Saurav Chandra Das, Toukir Ahammed, Md. Sanaullah Sanaullah, Dr. Mayna Talukdar

ACM Transactions on Asian and Low-Resource Language Information Processing · 19.11.2026

DOI: 10.1145/3864375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 19.11.2026. Verfasst von Koushik Biswas und 6 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sanskrit, one of the world’s oldest classical languages, holds a vast repository of historical, religious, and literary knowledge. Yet, most Bengali speakers face significant barriers accessing these resources due to language differences and the lack of effective Sanskrit-to-Bengali machine translation systems. To overcome this challenge, we developed a neural machine translation (NMT) system that translates Sanskrit texts into Bengali, assisted by a novel Sanskrit-Bengali translation dataset. Our main contribution involved manually compiling a parallel corpus of 31,639 Sanskrit-Bengali sentence pairs from religious scriptures, textbooks, tutorials, literary works, and existing translations. We trained and evaluated the transformer-based multilingual mBART model, pre-trained on several Indian languages, which shows enhanced translation performance in low-resource scenarios owing to its linguistic proximity to Sanskrit through both transfer learning and linguistic conceptual cross-lingual transfer. During fine-tuning, the model’s training BLEU score for Sanskrit-to-Bengali translation improved from 18 to 25.73. We evaluated the model using standard translation metrics and qualitative analysis. The results achieved were a BLEU score of 21.11, METEOR score of 40.10, ROUGE-1 score of 19.41, ROUGE-2 score of 8.72, ROUGE-L score of 19.29, chrF score of 41.41, and a TER of 77.83 on the test set. These results demonstrate that our method produces meaningful translations even with limited data.

Zitieren

APA

Biswas, K., Ghosh, R., Mahbub, M., Das, S. C., Ahammed, T., Sanaullah, M. S., & Talukdar, D. M. (2026). From Shloka to Shabda: Low-Resource Sanskrit to Bengali Translation. ACM Transactions on Asian and Low-Resource Language Information Processing. https://doi.org/10.1145/3864375

Vancouver

Biswas K, Ghosh R, Mahbub M, Das SC, Ahammed T, Sanaullah MS, et al. From Shloka to Shabda: Low-Resource Sanskrit to Bengali Translation. ACM Transactions on Asian and Low-Resource Language Information Processing. 2026. doi:10.1145/3864375

BibTeX
@article{Biswas2026,
  author = {Biswas, Koushik and Ghosh, Rupu and Mahbub, Mahir and Das, Saurav Chandra and Ahammed, Toukir and Sanaullah, Md. Sanaullah and Talukdar, Dr. Mayna},
  title = {From Shloka to Shabda: Low-Resource Sanskrit to Bengali Translation},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2026},
  doi = {10.1145/3864375}
}
Kostenlos starten →