@inproceedings{yaseen-langer-2021-data,
    title = "Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation",
    author = "Yaseen, Usama  and
      Langer, Stefan",
    editor = "Bandyopadhyay, Sivaji  and
      Devi, Sobha Lalitha  and
      Bhattacharyya, Pushpak",
    booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
    month = dec,
    year = "2021",
    address = "National Institute of Technology Silchar, Silchar, India",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.icon-main.43/",
    pages = "352--358",
    abstract = "The state of art natural language processing systems relies on sizable training datasets to achieve high performance. Lack of such datasets in the specialized low resource domains lead to suboptimal performance. In this work, we adapt backtranslation to generate high quality and linguistically diverse synthetic data for low-resource named entity recognition. We perform experiments on two datasets from the materials science (MaSciP) and biomedical (S800) domains. The empirical results demonstrate the effectiveness of our proposed augmentation strategy, particularly in the low-resource scenario."
}