@inproceedings{sutiono-hahn-powell-2022-syntax,
    title = "Syntax-driven Data Augmentation for Named Entity Recognition",
    author = "Sutiono, Arie  and
      Hahn-Powell, Gus",
    editor = "Chiticariu, Laura  and
      Goldberg, Yoav  and
      Hahn-Powell, Gus  and
      Morrison, Clayton T.  and
      Naik, Aakanksha  and
      Sharp, Rebecca  and
      Surdeanu, Mihai  and
      Valenzuela-Esc{\'a}rcega, Marco  and
      Noriega-Atala, Enrique",
    booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.pandl-1.7/",
    pages = "56--60",
    abstract = "In low resource settings, data augmentation strategies are commonly leveraged to improve performance. Numerous approaches have attempted document-level augmentation (e.g., text classification), but few studies have explored token-level augmentation. Performed naively, data augmentation can produce semantically incongruent and ungrammatical examples. In this work, we compare simple masked language model replacement and an augmentation method using constituency tree mutations to improve the performance of named entity recognition in low-resource settings with the aim of preserving linguistic cohesion of the augmented sentences."
}