@InProceedings{subedi-karki:2026:wmt,
  author    = {Subedi, Bipesh  and  Karki, Nischal},
  title     = {BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {2246--2253},
  abstract  = {This paper describes our submission to the WMT 2026 Low-Resource Indic Language Translation Shared Task for the English-Assamese and English-Bodo pairs in both translation directions. We fine-tune the pretrained NLLB-200 distilled 600M model for primary as well as contrastive tasks. Since Bodo is not supported by NLLB-200, we use the Hindi (hin\_Deva) language tag as a proxy for Bodo during fine-tuning and inference, based on an empirical evaluation of Devanagari-script language tags. The constrained systems are trained exclusively on the official task data, while the contrastive systems additionally incorporate publicly available parallel corpora, including AI4Bharat BPCC and Google Smol. A rigorous preprocessing pipeline, combined with the extra parallel data, yields consistent gains across all automatic metrics, with the largest improvements observed for the lower-resource English-Bodo pair.},
  url       = {https://aclanthology.org/2026.wmt-1.164}
}