Few-shot biomedical named entity recognition via knowledge-guided instance generation and prompt contrastive learning
Bioinformatics · 01.08.2023 · 39 (8)
DOI: 10.1093/bioinformatics/btad496 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.08.2023. Verfasst von Peng Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dalian Key Field Innovation Team, Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Few-shot learning that can effectively perform named entity recognition in low-resource scenarios has raised growing attention, but it has not been widely studied yet in the biomedical field. In contrast to high-resource domains, biomedical named entity recognition (BioNER) often encounters limited human-labeled data in real-world scenarios, leading to poor generalization performance when training only a few labeled instances. Recent approaches either leverage cross-domain high-resource data or fine-tune the pre-trained masked language model using limited labeled samples to generate new synthetic data, which is easily stuck in domain shift problems or yields low-quality synthetic data. Therefore, in this article, we study a more realistic scenario, i.e. few-shot learning for BioNER. Results Leveraging the domain knowledge graph, we propose knowledge-guided instance generation for few-shot BioNER, which generates diverse and novel entities based on similar semantic relations of neighbor nodes. In addition, by introducing question prompt, we cast BioNER as question-answering task and propose prompt contrastive learning to improve the robustness of the model by measuring the mutual information between query–answer pairs. Extensive experiments conducted on various few-shot settings show that the proposed framework achieves superior performance. Particularly, in a low-resource scenario with only 20 samples, our approach substantially outperforms recent state-of-the-art models on four benchmark datasets, achieving an average improvement of up to 7.1% F1. Availability and implementation Our source code and data are available at https://github.com/cpmss521/KGPC.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China.
- School of Computer Science and Engineering, Dalian Minzu University, Dalian 116600, China.
ORCID-Profile: Peng Chen, Zhihao Yang
Förderung
- Dalian Key Field Innovation Team
- Natural Science Foundation of China
Zitieren
APA
Chen, P., Wang, J., Lin, H., Zhao, D., & Yang, Z. (2023). Few-shot biomedical named entity recognition via knowledge-guided instance generation and prompt contrastive learning. Bioinformatics, 39(8). https://doi.org/10.1093/bioinformatics/btad496
Vancouver
Chen P, Wang J, Lin H, Zhao D, Yang Z. Few-shot biomedical named entity recognition via knowledge-guided instance generation and prompt contrastive learning. Bioinformatics. 2023;39(8). doi:10.1093/bioinformatics/btad496
BibTeX
@article{Chen2023,
author = {Chen, Peng and Wang, Jian and Lin, Hongfei and Zhao, Di and Yang, Zhihao},
title = {Few-shot biomedical named entity recognition via knowledge-guided instance generation and prompt contrastive learning},
journal = {Bioinformatics},
year = {2023},
volume = {39},
number = {8},
doi = {10.1093/bioinformatics/btad496}
}
EUVIMED