YMAI at SemEval-2022 Task 5: Detecting Misogyny in Memes using VisualBERT and MMBT MultiModal Pre-trained Models

Mohammad Habash, Yahya Daqour, Malak Abdullah, Mahmoud Al-Ayyoub


Abstract
This paper presents a deep learning system that contends at SemEval-2022 Task 5. The goal is to detect the existence of misogynous memes in sub-task A. At the same time, the advanced multi-label sub-task B categorizes the misogyny of misogynous memes into one of four types: stereotype, shaming, objectification, and violence. The Ensemble technique has been used for three multi-modal deep learning models: two MMBT models and VisualBERT. Our proposed system ranked 17 place out of 83 participant teams with an F1-score of 0.722 in sub-task A, which shows a significant performance improvement over the baseline model’s F1-score of 0.65.
Anthology ID:
2022.semeval-1.108
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
780–784
Language:
URL:
https://aclanthology.org/2022.semeval-1.108
DOI:
10.18653/v1/2022.semeval-1.108
Bibkey:
Cite (ACL):
Mohammad Habash, Yahya Daqour, Malak Abdullah, and Mahmoud Al-Ayyoub. 2022. YMAI at SemEval-2022 Task 5: Detecting Misogyny in Memes using VisualBERT and MMBT MultiModal Pre-trained Models. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 780–784, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
YMAI at SemEval-2022 Task 5: Detecting Misogyny in Memes using VisualBERT and MMBT MultiModal Pre-trained Models (Habash et al., SemEval 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.semeval-1.108.pdf