@inproceedings{de-lichy-etal-2021-meta,
    title = "Meta-Learning for Few-Shot Named Entity Recognition",
    author = "de Lichy, Cyprien  and
      Glaude, Hadrien  and
      Campbell, William",
    editor = "Lee, Hung-Yi  and
      Mohtarami, Mitra  and
      Li, Shang-Wen  and
      Jin, Di  and
      Korpusik, Mandy  and
      Dong, Shuyan  and
      Vu, Ngoc Thang  and
      Hakkani-Tur, Dilek",
    booktitle = "Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.metanlp-1.6/",
    doi = "10.18653/v1/2021.metanlp-1.6",
    pages = "44--58",
    abstract = "Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning algorithms. In this paper, we apply two meta-learning algorithms, Prototypical Networks and Reptile, to few-shot Named Entity Recognition (NER), including a method for incorporating language model pre-training and Conditional Random Fields (CRF). We propose a task generation scheme for converting classical NER datasets into the few-shot setting, for both training and evaluation. Using three public datasets, we show these meta-learning algorithms outperform a reasonable fine-tuned BERT baseline. In addition, we propose a novel combination of Prototypical Networks and Reptile."
}