@article{ding-etal-2026-self,
    title = "Self-supervised Data Augmentation for Text Classification in Low-Data Settings",
    author = "Ding, Deyu  and
      Wang, Mengying  and
      Spitz, Andreas",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.788/",
    pages = "10046--10056",
    abstract = "Due to data sparsity and high annotation cost, data augmentation has established itself as an effective tool for boosting model performance on supervised NLP tasks. Where task-agnostic augmentation methods tend to act as simple regularizers for the data, task-aware methods also leverage labels for the generation of data that are most suitable for downstream tasks. While prior work has investigated generation and sampling strategies individually, the potential of a self-supervised approach that leverages multiple pre-trained models in generation and sampling remains underexplored. To address this issue, we present an ensemble-based framework of language models that proposes augmentation candidates and internally reviews their suitability for low-resource text classification tasks. We evaluate our model on six classification benchmarks and find that it consistently outperforms state-of-the-art data augmentation baselines in classification accuracy by an average of 0.97 points in low-data scenarios."
}