@inproceedings{krasner-etal-2025-cross,
    title = "Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning",
    author = "Krasner, Nathaniel  and
      Lanuzo, Nicholas  and
      Anastasopoulos, Antonios",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-short.95/",
    pages = "1193--1199",
    ISBN = "979-8-89176-252-7",
    abstract = "Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. We investigate whether visual information can bridge this gap instead. Image caption datasets are very easy to create without requiring multilingual expertise, so this offers a more efficient alternative for low-resource languages. We find that multilingual image-caption alignment can implicitly align the text representations between languages, languages unseen by the encoder in pretraining can be incorporated into this alignment post-hoc, and these aligned representations are usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval."
}