RIT Boston at SemEval-2022 Task 5: Multimedia Misogyny Detection By Using Coherent Visual and Language Features from CLIP Model and Data-centric AI Principle

Lei Chen, Hou Wei Chou


Abstract
Detecting MEME images to be misogynous or not is an application useful on curbing online hateful information against women. In the SemEval-2022 Multimedia Automatic Misogyny Identification (MAMI) challenge, we designed a system using two simple but effective principles. First, we leverage on recently emerging Transformer models pre-trained (mostly in a self-supervised learning way) on massive data sets to obtain very effective visual (V) and language (L) features. In particular, we used the CLIP model provided by OpenAI to obtain coherent V and L features and then simply used a logistic regression model to make binary predictions. Second, we emphasized more on data rather than tweaking models by following the data-centric AI principle. These principles were proven to be useful and our final macro-F1 is 0.778 for the MAMI task A and ranked the third place among participant teams.
Anthology ID:
2022.semeval-1.87
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:
636–641
Language:
URL:
https://aclanthology.org/2022.semeval-1.87
DOI:
10.18653/v1/2022.semeval-1.87
Bibkey:
Cite (ACL):
Lei Chen and Hou Wei Chou. 2022. RIT Boston at SemEval-2022 Task 5: Multimedia Misogyny Detection By Using Coherent Visual and Language Features from CLIP Model and Data-centric AI Principle. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 636–641, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
RIT Boston at SemEval-2022 Task 5: Multimedia Misogyny Detection By Using Coherent Visual and Language Features from CLIP Model and Data-centric AI Principle (Chen & Chou, SemEval 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.semeval-1.87.pdf
Data
Hateful MemesHateful Memes Challenge