Memes are one of the most popular types of content used to spread information online. They can influence a large number of people through rhetorical and psychological techniques. The task, Detection of Persuasion Techniques in Texts and Images, is to detect these persuasive techniques in memes. It consists of three subtasks: (A) Multi-label classification using textual content, (B) Multi-label classification and span identification using textual content, and (C) Multi-label classification using visual and textual content. In this paper, we propose a transfer learning approach to fine-tune BERT-based models in different modalities. We also explore the effectiveness of ensembles of models trained in different modalities. We achieve an F1-score of 57.0, 48.2, and 52.1 in the corresponding subtasks.

翻译：Memes是用来在网上传播信息的最受欢迎的内容类型之一,它们可以通过言辞和心理技术对许多人产生影响。任务就是在文本和图像中检测劝导技术,目的是在Memes中检测这些有说服力的技术。它由三个子任务组成:(A) 使用文本内容的多标签分类,(B) 多标签分类和使用文本内容的横幅识别,(C) 使用视觉和文字内容的多标签分类。在本文中,我们建议以不同方式将学习方法转换为以微调的BERT为基础的模型。我们还探索以不同方式培训的模型组合的有效性。我们在相应的子任务中实现了57.0、48.2和52.1的F1分数。