Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation
ACM Transactions on Asian and Low-Resource Language Information Processing · 30.04.2026 · 25 (4) · 1-34
DOI: 10.1145/3800681 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 16.04.2026. Verfasst von Surangika Ranathunga und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben.
Abstract (Originalsprache)
Neural Machine Translation (NMT) systems built on multilingual sequence-to-sequence Language Models (msLMs) fail to deliver expected results when the amount of parallel data for a language, as well as the language’s representation in the model are limited. This restricts the capabilities of domain-specific NMT systems for low-resource languages (LRLs). As a solution, parallel data from auxiliary domains can be used either to fine-tune or to further pre-train the msLM. We present an evaluation of the effectiveness of these two techniques in the context of domain-specific LRL-NMT. We also explore the impact of domain divergence on NMT model performance. We recommend several strategies for utilizing auxiliary parallel data in building domain-specific NMT models for LRLs.
Zitieren
APA
Ranathunga, S., Nayak, S., Lee, E., Peng, X., Huang, S., Zeng, Y., Mao, Y., Su, T., Chan, Y., Yuan, S., & Rinaldi, A. (2026). Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation. ACM Transactions on Asian and Low-Resource Language Information Processing, 25(4), 1-34. https://doi.org/10.1145/3800681
Vancouver
Ranathunga S, Nayak S, Lee E, Peng X, Huang S, Zeng Y, et al. Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation. ACM Transactions on Asian and Low-Resource Language Information Processing. 2026;25(4):1-34. doi:10.1145/3800681
BibTeX
@article{Ranathunga2026,
author = {Ranathunga, Surangika and Nayak, Shravan and Lee, En-Shiun and Peng, Xin and Huang, Shih-Ting and Zeng, Yuchen and Mao, Yanke and Su, Tong and Chan, Yun-Hsiang and Yuan, Songchen and Rinaldi, Anthony},
title = {Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation},
journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
year = {2026},
volume = {25},
number = {4},
pages = {1--34},
doi = {10.1145/3800681}
}
EUVIMED