@inproceedings{frank-etal-2021-vision,
    title = "Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers",
    author = "Frank, Stella  and
      Bugliarello, Emanuele  and
      Elliott, Desmond",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.emnlp-main.775/",
    doi = "10.18653/v1/2021.emnlp-main.775",
    pages = "9847--9857"
}