Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes

Bin Ji, Shasha Li, Shaoduo Gan, Jie Yu, Jun Ma, Huijun Liu, Jing Yang


Abstract
Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples. However, existing prototypical networks for this task suffer from roughly estimated label dependency and closely distributed prototypes, thus often causing misclassifications. To address the above issues, we propose EP-Net, an Entity-level Prototypical Network enhanced by dispersedly distributed prototypes. EP-Net builds entity-level prototypes and considers text spans to be candidate entities, so it no longer requires the label dependency. In addition, EP-Net trains the prototypes from scratch to distribute them dispersedly and aligns spans to prototypes in the embedding space using a space projection. Experimental results on two evaluation tasks and the Few-NERD settings demonstrate that EP-Net consistently outperforms the previous strong models in terms of overall performance. Extensive analyses further validate the effectiveness of EP-Net.
Anthology ID:
2022.coling-1.159
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1842–1854
Language:
URL:
https://aclanthology.org/2022.coling-1.159
DOI:
Bibkey:
Cite (ACL):
Bin Ji, Shasha Li, Shaoduo Gan, Jie Yu, Jun Ma, Huijun Liu, and Jing Yang. 2022. Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1842–1854, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes (Ji et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.159.pdf
Data
Few-NERD