Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition

Youcheng Huang, Wenqiang Lei, Jie Fu, Jiancheng Lv


Abstract
Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition. Existing methods, unfortunately, are not aware of the fact that embeddings from pre-trained models contain a prominently large amount of information regarding word frequencies, biasing prototypical neural networks against learning word entities. This discrepancy constrains the two models’ synergy. Thus, we propose a one-line-code normalization method to reconcile such a mismatch with empirical and theoretical grounds. Our experiments based on nine benchmark datasets show the superiority of our method over the counterpart models and are comparable to the state-of-the-art methods. In addition to the model enhancement, our work also provides an analytical viewpoint for addressing the general problems in few-shot name entity recognition or other tasks that rely on pre-trained models or prototypical neural networks.
Anthology ID:
2022.findings-emnlp.129
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1793–1807
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.129
DOI:
10.18653/v1/2022.findings-emnlp.129
Bibkey:
Cite (ACL):
Youcheng Huang, Wenqiang Lei, Jie Fu, and Jiancheng Lv. 2022. Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1793–1807, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition (Huang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.129.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.129.mp4