A Novel Three-stage Framework for Few-shot Named Entity Recognition

Shengjie Ji, Fang Kong

Abstract
Different from most existing tasks relying on abundant labeled data, Few-shot Named Entity Recognition (NER) aims to develop NER systems that are capable of learning from a small set of labeled samples and then generalizing well to new, unseen data.In this paper, with the intention of obtaining a model that can better adapt to new domains, we design a novel three-stage framework for Few-shot NER, including teacher span recognizer, student span recognizer and entity classifier.We first train a teacher span recognizer which is based on a global boundary matrix to obtain soft boundary labels.Then we leverage the soft boundary labels learned by the teacher model to assist in training the student span recognizer,which can smooth the training process of span recognizer.Finally, we adopt the traditional prototypical network as entity classifier and incorporate the idea of prompt learning to construct a more generalizable semantic space.Extensive experiments on various benchmarks demonstrate that our approach surpasses prior methods.
Anthology ID:
2024.lrec-main.116
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
1293–1305
Language:
URL:
https://aclanthology.org/2024.lrec-main.116
DOI:
Bibkey:
Cite (ACL):
Shengjie Ji and Fang Kong. 2024. A Novel Three-stage Framework for Few-shot Named Entity Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1293–1305, Torino, Italia. ELRA and ICCL.
Cite (Informal):
A Novel Three-stage Framework for Few-shot Named Entity Recognition (Ji & Kong, LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.116.pdf
PDF Search