@inproceedings{mijatovic-etal-2023-rcln,
    title = "{RCLN} at {S}em{E}val-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual {WSD}",
    author = "Mijatovic, Antonina  and
      Buscaldi, Davide  and
      Borisova, Ekaterina",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.semeval-1.301/",
    doi = "10.18653/v1/2023.semeval-1.301",
    pages = "2174--2178",
    abstract = "This paper describes the participation of the RCLN team at the Visual Word Sense Disambiguation task at SemEval 2023. The participation was focused on the use of CLIP as a base model for the matching between text and images with additional information coming from captions generated from images and the generation of images from the prompt text using Stable Diffusion. The results we obtained are not particularly good, but interestingly enough, we were able to improve over the CLIP baseline in Italian by recurring simply to the generated images."
}