@inproceedings{li-etal-2021-1213li,
    title = "1213{L}i at {S}em{E}val-2021 Task 6: Detection of Propaganda with Multi-modal Attention and Pre-trained Models",
    author = "Li, Peiguang  and
      Li, Xuan  and
      Sun, Xian",
    editor = "Palmer, Alexis  and
      Schneider, Nathan  and
      Schluter, Natalie  and
      Emerson, Guy  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan",
    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.semeval-1.142/",
    doi = "10.18653/v1/2021.semeval-1.142",
    pages = "1032--1036",
    abstract = "This paper presents the solution proposed by the 1213Li team for subtask 3 in SemEval-2021 Task 6: identifying the multiple persuasion techniques used in the multi-modal content of the meme. We explored various approaches in feature extraction and the detection of persuasion labels. Our final model employs pre-trained models including RoBERTa and ResNet-50 as a feature extractor for texts and images, respectively, and adopts a label embedding layer with multi-modal attention mechanism to measure the similarity of labels with the multi-modal information and fuse features for label prediction. Our proposed method outperforms the provided baseline method and achieves 3rd out of 16 participants with 0.54860/0.22830 for Micro/Macro F1 scores."
}