@inproceedings{kanojia-2025-challenge,
    title = "Challenge Track: Divide and Translate: Parameter Isolation with Encoder Freezing for Low-Resource {I}ndic {NMT}",
    author = "Kanojia, Vaibhav",
    editor = "Shukla, Ankita  and
      Kumar, Sandeep  and
      Bedi, Amrit Singh  and
      Chakraborty, Tanmoy",
    booktitle = "Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.mmloso-1.12/",
    pages = "109--113",
    ISBN = "979-8-89176-311-1",
    abstract = "We present a direction-specialized neural machine translation framework for ultra-low-resource Indic and tribal languages, including Bhili, Gondi, Mundari, and Santali. Using the NLLB-600M backbone, we freeze the multilingual encoder and fine-tune direction-specific decoders to reduce negative transfer and improve morphological fidelity under severe data scarcity. Our system is trained with leakage-safe splits, bitext reversal augmentation, and memory-efficient mixed-precision optimization. On the official MMLoSo 2025 Kaggle benchmark, we achieve a public score of 171.4 and a private score of 161.1, demonstrating stable generalization in highly noisy low-resource conditions."
}