@InProceedings{chakma-EtAl:2026:wmt,
  author    = {Chakma, Aunabil  and  Chakma, Aditya  and  Hasan, Masum  and  Khisa, Soham  and  Tripura, Chumui  and  Shahriyar, Rifat},
  title     = {ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {64--81},
  abstract  = {We present a systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language. We introduce a large Chakma–Bangla machine translation resource comprising 15,021 parallel translation pairs, 42,783 Chakma monolingual sentences, and a trilingual evaluation benchmark. To address data scarcity and the script mismatch between Chakma and Bangla, we develop a character-level transliteration framework that enables transfer from Bangla and multilingual pretrained models. We evaluate from-scratch machine translation systems, fine-tuned pretrained models, and large language models using in-context learning. Our results show that transliteration is crucial for the tested pretrained models and that performance is strongly direction-dependent: in-context learning performs best for Chakma-to-Bangla translation, while Bangla-to-Chakma remains considerably more challenging, with the strongest approach depending on the evaluation metric.},
  url       = {https://aclanthology.org/2026.wmt-1.5}
}