الميمات هي واحدة من الأنواع الأكثر شعبية من المحتوى المستخدمة لنشر المعلومات عبر الإنترنت.يمكنهم التأثير على عدد كبير من الناس من خلال التقنيات الخطابية والنفسية.تتمثل المهمة والكشف عن تقنيات الإقناع في النصوص والصور، والكشف عن هذه التقنيات المقنعة في الميمات.يتكون من ثلاثة أجهزة فرعية: (أ) تصنيف متعدد التسميات باستخدام المحتوى النصي، (ب) تصنيف التسميات المتعددة والتحديد SPAN باستخدام المحتوى النصي، و (ج) تصنيف متعدد التسميات باستخدام المحتوى المرئي والنصوص.في هذه الورقة، نقترح نهجا للتعلم نقل النماذج القائمة على Brote-Tune-Tune في طرائق مختلفة.نحن نستكشف أيضا فعالية مجموعات النماذج المدربة في طرائق مختلفة.نحقق درجة F1 57.0 و 48.2 و 52.1 في المهام الفرعية المقابلة.
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.
References used
https://aclanthology.org/
We describe SemEval-2021 task 6 on Detection of Persuasion Techniques in Texts and Images: the data, the annotation guidelines, the evaluation setup, the results, and the participating systems. The task focused on memes and had three subtasks: (i) de
The following system description presents our approach to the detection of persuasion techniques in texts and images. The given task has been framed as a multi-label classification problem with the different techniques serving as class labels. The mu
We describe our approach for SemEval-2021 task 6 on detection of persuasion techniques in multimodal content (memes). Our system combines pretrained multimodal models (CLIP) and chained classifiers. Also, we propose to enrich the data by a data augmentation technique. Our submission achieves a rank of 8/16 in terms of F1-micro and 9/16 with F1-macro on the test set.
Inscribing persuasion techniques in memes is the most impactful way to influence peoples' mindsets. People are more inclined to memes as they are more stimulating and convincing and hence memes are often exploited by tactfully engraving propaganda in
This paper describes the system used by the AIMH Team to approach the SemEval Task 6. We propose an approach that relies on an architecture based on the transformer model to process multimodal content (text and images) in memes. Our architecture, cal