@inproceedings{francis-moens-2024-kul,
    title = "{KUL}@{SMM}4{H}2024: Optimizing Text Classification with Quality-Assured Augmentation Strategies",
    author = "Francis, Sumam  and
      Moens, Marie-Francine",
    editor = "Xu, Dongfang  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.smm4h-1.33/",
    pages = "142--145",
    abstract = "This paper presents our models for the Social Media Mining for Health 2024 shared task, specifically Task 5, which involves classifying tweets reporting a child with childhood disorders (annotated as {\textquotedblleft}1{\textquotedblright}) versus those merely mentioning a disorder (annotated as {\textquotedblleft}0{\textquotedblright}). We utilized a classification model enhanced with diverse textual and language model-based augmentations. To ensure quality, we used semantic similarity, perplexity, and lexical diversity as evaluation metrics. Combining supervised contrastive learning and cross-entropy-based learning, our best model, incorporating R-drop and various LM generation-based augmentations, achieved an impressive F1 score of 0.9230 on the test set, surpassing the task mean and median scores."
}