@inproceedings{dai-adel-2020-analysis,
    title = "An Analysis of Simple Data Augmentation for Named Entity Recognition",
    author = "Dai, Xiang  and
      Adel, Heike",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.coling-main.343/",
    doi = "10.18653/v1/2020.coling-main.343",
    pages = "3861--3867",
    abstract = "Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity recognition, which is usually modeled as a token-level sequence labeling problem. Through experiments on two data sets from the biomedical and materials science domains (i2b2-2010 and MaSciP), we show that simple augmentation can boost performance for both recurrent and transformer-based models, especially for small training sets."
}