Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition

Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, Yunsen Xian


Abstract
Prompt-based methods have been widely used in few-shot named entity recognition (NER). In this paper, we first conduct a preliminary experiment and observe that the key to affecting the performance of prompt-based NER models is the capability to detect entity boundaries. However, most existing models fail to boost such capability. To solve the issue, we propose a novel model, ParaBART, which consists of a BART encoder and a specially designed parabiotic decoder. Specifically, the parabiotic decoder includes two BART decoders and a conjoint module. The two decoders are responsible for entity boundary detection and entity type classification, respectively. They are connected by the conjoint module, which is used to replace unimportant tokens’ embeddings in one decoder with the average embedding of all the tokens in the other. We further present a novel boundary expansion strategy to enhance the model’s capability in entity type classification. Experimental results show that ParaBART can achieve significant performance gains over state-of-the-art competitors.
Anthology ID:
2024.lrec-main.329
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:
3707–3717
Language:
URL:
https://aclanthology.org/2024.lrec-main.329
DOI:
Bibkey:
Cite (ACL):
Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, and Yunsen Xian. 2024. Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3707–3717, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition (Han et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.329.pdf