@inproceedings{koontz-etal-2023-evaluating,
    title = "Evaluating Data Augmentation for Medication Identification in Clinical Notes",
    author = "Koontz, Jordan  and
      Oronoz, Maite  and
      P{\'e}rez, Alicia",
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
    month = sep,
    year = "2023",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.ranlp-1.63/",
    pages = "578--585",
    abstract = "We evaluate the effectiveness of using data augmentation to improve the generalizability of a Named Entity Recognition model for the task of medication identification in clinical notes. We compare disparate data augmentation methods, namely mention-replacement and a generative model, for creating synthetic training examples. Through experiments on the n2c2 2022 Track 1 Contextualized Medication Event Extraction data set, we show that data augmentation with supplemental examples created with GPT-3 can boost the performance of a transformer-based model for small training sets."
}