%0 Conference Proceedings
%T 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
%A Chen, Lei
%A Chou, Hou Wei
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F chen-chou-2022-rit
%X 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.
%R 10.18653/v1/2022.semeval-1.87
%U https://aclanthology.org/2022.semeval-1.87
%U https://doi.org/10.18653/v1/2022.semeval-1.87
%P 636-641