SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition

Jianing Wang, Chengyu Wang, Chuanqi Tan, Minghui Qiu, Songfang Huang, Jun Huang, Ming Gao


Abstract
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.
Anthology ID:
2022.emnlp-main.227
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3466–3476
Language:
URL:
https://aclanthology.org/2022.emnlp-main.227
DOI:
10.18653/v1/2022.emnlp-main.227
Bibkey:
Cite (ACL):
Jianing Wang, Chengyu Wang, Chuanqi Tan, Minghui Qiu, Songfang Huang, Jun Huang, and Ming Gao. 2022. SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3466–3476, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition (Wang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.227.pdf