@inproceedings{parida-etal-2024-odiagenais,
    title = "{O}dia{G}en{AI}`s Participation in {WMT}2024 {E}nglish-to-Low Resource Multimodal Translation Task",
    author = "Parida, Shantipriya  and
      Sahoo, Shashikanta  and
      Sekhar, Sambit  and
      Jena, Upendra  and
      Jena, Sushovan  and
      Lata, Kusum",
    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-1.77/",
    doi = "10.18653/v1/2024.wmt-1.77",
    pages = "823--828",
    abstract = "This paper covers the system description of the team {\textquotedblleft}ODIAGEN`s{\textquotedblright} submission to the WMT{\textasciitilde}2024 English-to-Low-Resource Multimodal Translation Task. We participated in the English-to-Low Resource Multimodal Translation Task, in two of the tasks, i.e. Text-only Translation and Multi-modal Translation. For Text-only Translation, we trained the Mistral-7B model for English to Multi-lingual (Hindi, Bengali, Malayalam, Hausa). For Multi-modal Translation (using both image and text), we trained the PaliGemma-3B model for English to Hindi translation."
}