@inproceedings{diem-etal-2023-university,
    title = "{U}niversity of {H}ildesheim at {S}em{E}val-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation",
    author = "Diem, Sebastian  and
      Im, Chan Jong  and
      Mandl, Thomas",
    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-1.18/",
    doi = "10.18653/v1/2023.semeval-1.18",
    pages = "130--135",
    abstract = "Multimodal ambiguity is a challenge for understanding text and images. Large pre-trained models have reached a high level of quality already. This paper presents an implementation for solving a image disambiguation task relying solely on the knowledge captured in multimodal and language models. Within the task 1 of SemEval 2023 (Visual Word Sense Disambiguation), this approach managed to achieve an MRR of 0.738 using CLIP-Large and the OPT model for generating text. Applying a generative model to create more text given a phrase with an ambiguous word leads to an improvement of our results. The performance gain from a bigger language model is larger than the performance gain from using the lager CLIP model."
}