nowhash at SemEval-2024 Task 4: Exploiting Fusion of Transformers for Detecting Persuasion Techniques in Multilingual Memes

Abu Nowhash Chowdhury, Michal Ptaszynski


Abstract
Nowadays, memes are considered one of the most prominent forms of medium to disseminate information on social media. Memes are typically constructed in multilingual settings using visuals with texts. Sometimes people use memes to influence mass audiences through rhetorical and psychological techniques, such as causal oversimplification, name-calling, and smear. It is a challenging task to identify those techniques considering memes’ multimodal characteristics. To address these challenges, SemEval-2024 Task 4 introduced a shared task focusing on detecting persuasion techniques in multilingual memes. This paper presents our participation in subtasks 1 and 2(b). We use a finetuned language-agnostic BERT sentence embedding (LaBSE) model to extract effective contextual features from meme text to address the challenge of identifying persuasion techniques in subtask 1. For subtask 2(b), We finetune the vision transformer and XLM-RoBERTa to extract effective contextual information from meme image and text data. Finally, we unify those features and employ a single feed-forward linear layer on top to obtain the prediction label. Experimental results on the SemEval 2024 Task 4 benchmark dataset manifested the potency of our proposed methods for subtasks 1 and 2(b).
Anthology ID:
2024.semeval-1.21
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
133–138
Language:
URL:
https://aclanthology.org/2024.semeval-1.21
DOI:
10.18653/v1/2024.semeval-1.21
Bibkey:
Cite (ACL):
Abu Nowhash Chowdhury and Michal Ptaszynski. 2024. nowhash at SemEval-2024 Task 4: Exploiting Fusion of Transformers for Detecting Persuasion Techniques in Multilingual Memes. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 133–138, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
nowhash at SemEval-2024 Task 4: Exploiting Fusion of Transformers for Detecting Persuasion Techniques in Multilingual Memes (Chowdhury & Ptaszynski, SemEval 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.semeval-1.21.pdf
Supplementary material:
 2024.semeval-1.21.SupplementaryMaterial.txt