@inproceedings{patil-etal-2024-srib,
    title = "{SRIB}-{NMT}`s Submission to the {I}ndic {MT} Shared Task in {WMT} 2024",
    author = "Patil, Pranamya  and
      Hr, Raghavendra  and
      Raghuwanshi, Aditya  and
      Verma, Kushal",
    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-emnlp-2024-awards/2024.wmt-1.64/",
    doi = "10.18653/v1/2024.wmt-1.64",
    pages = "747--750",
    abstract = "In the context of the Indic Low Resource Ma-chine Translation (MT) challenge at WMT-24, we participated in four language pairs:English-Assamese (en-as), English-Mizo (en-mz), English-Khasi (en-kh), and English-Manipuri (en-mn). To address these tasks,we employed a transformer-based sequence-to-sequence architecture (Vaswani et al., 2017).In the PRIMARY system, which did not uti-lize external data, we first pretrained languagemodels (low resource languages) using avail-able monolingual data before finetuning themon small parallel datasets for translation. Forthe CONTRASTIVE submission approach, weutilized pretrained translation models like In-dic Trans2 (Gala et al., 2023) and appliedLoRA Fine-tuning (Hu et al., 2021) to adaptthem to smaller, low-resource languages, aim-ing to leverage cross-lingual language transfercapabilities (CONNEAU and Lample, 2019).These approaches resulted in significant im-provements in SacreBLEU scores(Post, 2018)for low-resource languages."
}