@inproceedings{zhang-etal-2023-gpl,
    title = "{GPL} at {S}em{E}val-2023 Task 1: {W}ord{N}et and {CLIP} to Disambiguate Images",
    author = "Zhang, Shibingfeng  and
      Nath, Shantanu  and
      Mazzaccara, Davide",
    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/add-emnlp-2024-awards/2023.semeval-1.219/",
    doi = "10.18653/v1/2023.semeval-1.219",
    pages = "1592--1597",
    abstract = "Given a word in context, the task of VisualWord Sense Disambiguation consists of select-ing the correct image among a set of candidates. To select the correct image, we propose a so-lution blending text augmentation and multi-modal models. Text augmentation leverages thefine-grained semantic annotation from Word-Net to get a better representation of the tex-tual component. We then compare this sense-augmented text to the set of image using pre-trained multimodal models CLIP and ViLT. Oursystem has been ranked 16th for the Englishlanguage, achieving 68.5 points for hit rate and79.2 for mean reciprocal rank."
}