@inproceedings{sahoo-etal-2024-nlip,
    title = "{NLIP}{\_}{L}ab-{IITH} Low-Resource {MT} System for {WMT}24 {I}ndic {MT} Shared Task",
    author = "Sahoo, Pramit  and
      Brahma, Maharaj  and
      Desarkar, Maunendra Sankar",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Ninth Conference on Machine Translation",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.wmt-1.70/",
    doi = "10.18653/v1/2024.wmt-1.70",
    pages = "781--787",
    abstract = "In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng{\ensuremath{\leftrightarrow}}{\{}as, kha, lus, mni{\}} as participating language pairs. In this shared task, we explore the fine-tuning of a pre-trained model motivated by the pre-trained objective of aligning embeddings closer by alignment augmentation (Lin et al.,2020) for 22 scheduled Indian languages. Our primary system is based on language-specific finetuning on a pre-trained model. We achieve chrF2 scores of 50.6, 42.3, 54.9, and 66.3 on the official public test set for eng{\textrightarrow}as, eng{\textrightarrow}kha, eng{\textrightarrow}lus, eng{\textrightarrow}mni respectively. We also explore multilingual training with/without language grouping and layer-freezing."
}