Tsingriver at SemEval-2023 Task 10: Labeled Data Augmentation in Consistency Training

Yehui Xu, Haiyan Ding

The 17th International Workshop on Semantic Evaluation (SemEval-2023) Task 10: towards explainable detection of online sexism Paper

TLDR: Semi-supervised learning has promising performance in deep learning, one of the approaches is consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. However, The degree of correlation between unlabeled data and task objective directly
You can open the #paper-SemEval_121 channel in a separate window.
Abstract: Semi-supervised learning has promising performance in deep learning, one of the approaches is consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. However, The degree of correlation between unlabeled data and task objective directly affects model prediction performance. This paper describes our system designed for SemEval-2023 Task 10: Explainable Detection of Online Sexism. We utilize a consistency training framework and data augmentation as the main strategy to train a model. The score obtained by our method is 0.8180 in subtask A, ranking 57 in all the teams.