TULUN: Transparent and Adaptable Low-resource Machine Translation
: Merx, Raphael; Suominen, Hanna; Hong, Lois Yinghui; Thieberger, Nick; Cohn, Trevor; Vylomova, Ekaterina
: Mishra, Pushkar; Muresan, Smaranda; Yu, Tao
: Annual Meeting of the Association for Computational Linguistics
Publisher: ASSOC COMPUTATIONAL LINGUISTICS-ACL
: 2025
Annual Meeting of the Association for Computational Linguistics
: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics : (Volume 3: System Demonstrations)
: 63
: 129
: 139
: 979-8-89176-253-4
: 0736-587X
DOI: https://doi.org/10.18653/v1/2025.acl-demo.13
: https://aclanthology.org/2025.acl-demo.13/
: https://research.utu.fi/converis/portal/detail/Publication/506057677
Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation, these approaches typically require model fine-tuning, making them impractical for non-technical users and small organizations. To address this gap, we propose TULUN,(1) a versatile solution for terminology-aware translation, combining neural MT with large language model (LLM)-based post-editing guided by existing glossaries and translation memories. Our open-source web-based platform enables users to easily create, edit, and leverage terminology resources, fostering a collaborative human-machine translation process that respects and incorporates domain expertise while increasing MT accuracy. Evaluations show effectiveness in both real-world and benchmark scenarios: on medical and disaster relief translation tasks for Tetun and Bislama, our system achieves improvements of 16.90-22.41 ChrF++ points over baseline MT systems. Across six low-resource languages on the FLORES dataset, TULUN outperforms both standalone MT and LLM approaches, achieving an average improvement of 2.8 ChrF++ points over NLLB-54B. TULUN is publicly accessible at bislama-trans.rapha.dev.
:
This research was supported by The University of Melbourne’s Research Computing Services and the Petascale Campus Initiative.
