@inproceedings{anghelina-etal-2024-sutealbastre,
    title = "{S}ute{A}lbastre at {S}em{E}val-2024 Task 4: Predicting Propaganda Techniques in Multilingual Memes using Joint Text and Vision Transformers",
    author = "Anghelina, Ion  and
      Buț{\u{a}}, Gabriel  and
      Enache, Alexandru",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.semeval-1.68/",
    doi = "10.18653/v1/2024.semeval-1.68",
    pages = "443--449",
    abstract = "The main goal of this year{'}s SemEval Task 4 isdetecting the presence of persuasion techniquesin various meme formats. While Subtask 1targets text-only posts, Subtask 2, subsectionsa and b tackle posts containing both imagesand captions. The first 2 subtasks consist ofmulti-class and multi-label classifications, inthe context of a hierarchical taxonomy of 22different persuasion techniques.This paper proposes a solution for persuasiondetection in both these scenarios and for vari-ous languages of the caption text. Our team{'}smain approach consists of a Multimodal Learn-ing Neural Network architecture, having Tex-tual and Vision Transformers as its backbone.The models that we have experimented with in-clude EfficientNet and ViT as visual encodersand BERT and GPT2 as textual encoders."
}