Despite the huge and continuous advances in computational linguistics, the lack of annotated data for Named Entity Recognition (NER) is still a challenging issue, especially in low-resource languages and when domain knowledge is required for high-quality annotations. Recent findings in NLP show the effectiveness of cloze-style questions in enabling language models to leverage the knowledge they acquired during the pre-training phase. In our work, we propose a simple and intuitive adaptation of Pattern-Exploiting Training (PET), a recent approach which combines the cloze-questions mechanism and fine-tuning for few-shot learning: the key idea is to rephrase the NER task with patterns. Our approach achieves considerably better performance than standard fine-tuning and comparable or improved results with respect to other few-shot baselines without relying on manually annotated data or distant supervision on three benchmark datasets: NCBI-disease, BC2GM and a private Italian biomedical corpus.
@article{arxiv.2111.12421,
title = {Few-shot Named Entity Recognition with Cloze Questions},
author = {Valerio La Gatta and Vincenzo Moscato and Marco Postiglione and Giancarlo Sperlì},
journal= {arXiv preprint arXiv:2111.12421},
year = {2021}
}