@InProceedings{arora-EtAl:2026:wmt2,
  author    = {Arora, Palak  and  Ahmed, Syed Afroz  and  Jangid, Mansi  and  Nathani, Bharti  and  Joshi, Nisheeth},
  title     = {BVSLP at WMT 2026: An Empirical Study of Multilingual Transfer for Low-Resource Arabic-Centric Translation},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {2280--2286},
  abstract  = {This paper presents HEMANT framework, the BSVLP submission to the WMT 2026 Low-Resource Arabic–Asian Machine Translation Shared Task. The system addresses ten bidirectional translation directions involving Arabic, English, Hindi, Bangla, Indonesian, and Urdu. HEMANT integrates language-specific Unicode normalization, spelling correction, named-entity recognition, knowledge-base-assisted entity translation, transliteration, multilingual transfer learning, and parameter-efficient adaptation of the NLLB-200 model using LoRA. Two directional multilingual models were trained for many-to-Arabic and Arabic-to-many translations. The official results showed considerable variation across language pairs. Arabic–Hindi produced the strongest relative performance, while English–Arabic remained the most challenging pair. In several directions, COMET scores were more competitive than BLEU and TER, suggesting that semantic adequacy was often better preserved than lexical overlap. The findings highlight both the potential and limitations of entity-aware multilingual adaptation for low-resource Arabic–Asian translation.},
  url       = {https://aclanthology.org/2026.wmt-1.168}
}