Few-Shot Named Entity Recognition Method Based on Distribution Calibration

doi:10.19678/j.issn.1000-3428.0070449

Computer Engineering ›› 2026, Vol. 52 ›› Issue (9): 143-153. doi: 10.19678/j.issn.1000-3428.0070449

• Computational Intelligence and Pattern Recognition • Previous Articles Next Articles

Few-Shot Named Entity Recognition Method Based on Distribution Calibration

PU Zhenyu¹, LIU Zhiwei¹, HUANG Bo¹^,²^,*(), HE Shufeng³, CHEN Nanxi⁴, XI Wenzeng⁵

1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
2. Engineering Research Center for Intelligent Technology for Agricultural, Ministry of Education, Huazhong Agricultural University, Wuhan 430070, Hubei, China
3. Qingdao Institute of Marine Geology, China Geological Survey, Qingdao 266071, Shandong, China
4. Shanghai Institute of Microsystem and Information Technology, Chinese Acadamy of Sciences, Shanghai 200050, China
5. Tianjin SDIC JinNeng Electric Power Co., Ltd., Tianjin 100032, China

Received:2024-10-09 Revised:2025-02-13 Online:2026-09-15 Published:2025-04-25
Contact: HUANG Bo

基于分布校正的小样本命名实体识别方法

浦震宇¹, 刘志伟¹, 黄勃¹^,²^,*(), 何书锋³, 陈南希⁴, 郗文增⁵

1. 上海工程技术大学电子电气工程学院, 上海 201620
2. 华中农业大学农业智能技术教育部工程研究中心, 湖北武汉 430070
3. 中国地质调查局青岛海洋地质研究所, 山东青岛 266071
4. 中国科学院上海微系统与信息技术研究所, 上海 200050
5. 天津国投津能发电有限公司, 天津 100032

通讯作者: 黄勃
作者简介:
浦震宇, 男, 硕士研究生, 主研方向为自然语言处理
刘志伟, 硕士研究生
黄勃(通信作者), 副教授
何书锋, 高级工程师
陈南希, 副研究员
郗文增, 高级工程师
基金资助:
华中农业大学农业智能技术教育部工程研究中心开放课题(ERCITA-KF002)

Abstract

Abstract:

In the modern industrial sector, the perception and analysis of text data are essential for promoting intelligent manufacturing and optimizing production processes. However, industrial text data are typically characterized by high specialization, diversity, complexity, and annotation costs, making traditional large-scale annotation methods unsuitable. Existing few-shot Named Entity Recognition (NER) methods often use prototypical networks to classify entities, where the prototype is the average of the features of all samples belonging to the same category. However, these methods are highly sensitive to the support set data and prone to sample-selection bias. To address this, a few-shot NER model based on Distribution Calibration called DC-NER is proposed. A two-stage approach for span detection and entity classification is adopted for the few-shot NER task. In the first stage, an entity extractor is used to select candidate entities. In the second stage, a type discriminator assigns these entities to predefined categories. To address the challenge of capturing the true class distribution with a small number of labeled samples in few-shot NER, which leads to inaccurate class prototype calculations, a method is proposed that leverages useful information from the source domain data to calibrate the class distribution in the target domain. Thus, more samples are generated based on the refined class distribution to construct more accurate prototypes, thereby improving the performance in few-shot NER tasks. Experiments on both the in-domain dataset Few-NERD and the cross-domain dataset Cross-NER reveal that DC-NER significantly outperforms the comparative models in terms of F1 value, validating its effectiveness for few-shot NER.

Key words: industrial text data, Named Entity Recognition (NER), few-shot learning, prototypical network, distribution calibration

摘要：

在现代工业领域, 文本数据的感知和分析已成为推动智能制造和优化生产流程的重要手段。然而, 工业文本数据通常具有高专业性、多样性和复杂性等特点, 且标注成本较高, 因此传统的大规模标注方法难以适用。现有的小样本命名实体识别(NER)方法多采用原型网络对实体进行分类, 其中原型为属于同一类别的所有样本特征的平均值。然而, 这类方法对于支持集数据的敏感性较强, 容易出现样本选择性偏差的问题。为此, 提出基于分布校正的小样本命名实体识别(DC-NER)模型。采用跨度检测和实体分类两阶段方式进行小样本NER任务, 在第1个阶段, 利用实体抽取器选出候选实体, 在第2个阶段, 利用类型判别器将实体划分到预定义好的类别。为了解决小样本NER任务中利用少量标签样本难以捕捉到类别真实分布的问题, 进而使得类原型的计算不够准确, 提出一种利用源域数据中的有效信息校正目标域的类别分布, 进而通过改进后的类别分布生成更多的样本用于构建更准确的原型, 从而提高其在小样本NER任务中的性能。在同领域数据集Few-NERD和跨领域数据集Cross-NER上的实验结果表明, DC-NER在F1值上显著优于对比模型, 验证其在小样本NER中的有效性。

关键词: 工业文本数据, 命名实体识别, 小样本学习, 原型网络, 分布校正

PU Zhenyu, LIU Zhiwei, HUANG Bo, HE Shufeng, CHEN Nanxi, XI Wenzeng. Few-Shot Named Entity Recognition Method Based on Distribution Calibration[J]. Computer Engineering, 2026, 52(9): 143-153.

浦震宇, 刘志伟, 黄勃, 何书锋, 陈南希, 郗文增. 基于分布校正的小样本命名实体识别方法[J]. 计算机工程, 2026, 52(9): 143-153.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070449

https://www.ecice06.com/EN/Y2026/V52/I9/143

Figures/Tables 13

Fig.1 DC-NER architecture

Fig.2 Experimental results of DC-NER and comparison models under Few-NERD Inter dataset

Fig.3 Experimental results of DC-NER and comparison models under Few-NERD Intra dataset

Fig.4 Experimental results of model performance with varying sampling sizes

Fig.5 Experimental results of DC-NER and comparison models under cross-domain dataset 1-shot

Fig.6 Experimental results of DC-NER and comparison models under cross-domain dataset 5-shot

References 35

1	LI J , SUN A , HAN J L , et al. A survey on deep learning for named entity recognition. IEEE Transactions on Knowledge and Data Engineering, 2020, 34 (1): 50- 70.
2	WEBER L, SANGER M, MUNCHMEYER J, et al. HunFlair: an easy-to-use tool for state-of-the-art biomedical named entity recognition[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2008.07347.
3	ALFRED R , LEONG L C , ON C K , et al. Malay named entity recognition based on rule-based approach. International Journal of Machine Learning and Computing, 2014, 4 (3): 300- 306. doi: 10.7763/IJMLC.2014.V4.428
4	QUIMBAYA A P , MÚNERA A S , RIVERA R A G , et al. Named entity recognition over electronic health records through a combined dictionary-based approach. Procedia Computer Science, 2016, 100, 55- 61. doi: 10.1016/j.procs.2016.09.123
5	KONKOL M, KONOPÍK M. CRF-based Czech named entity recognizer and consolidation of Czech NER research[C]//Proceedings of the 16th International Conference on Text, Speech. Berlin, Germany: Springer, 2013: 153-160.
6	张红民, 颜鼎鼎, 田钱前. 改进时空图卷积网络的视频异常检测方法. 光电工程, 2024, 51 (5): 240034.
	ZHANG H M , YAN D D , TIAN Q Q . Improved spatio-temporal graph convolutional networks for video anomaly detection. Opto-Electronic Engineering, 2024, 51 (5): 240034.
7	LIN B Y, XU F F, LUO Z Y, et al. Multi-channel BiLSTM-CRF model for emerging named entity recognition in social media[C]//Proceedings of the 3rd Workshop on Noisy User-Generated Text. San Diego, USA: Association for Computational Linguistics, 2017: 160-165.
8	陈雪松, 朱鑫海, 王浩畅. 基于PMV-LSTM的中文医学命名实体识别. 计算机工程与设计, 2022, 43 (11): 3257- 3263.
	CHEN X S , ZHU X H , WANG H C . Chinese medical named entity recognition based on PMV-LSTM. Computer Engineering and Design, 2022, 43 (11): 3257- 3263.
9	夏成魁, 李少波. 基于BERT-BiLSTM-MHA-CRF的中文命名实体识别方法. 计算机与数字工程, 2023, 51 (9): 2087-2091, 2102.
	XIA C K , LI S B . Chinese named entity recognition method based on BERT-BiLSTM-MHA-CRF model. Computer and Digital Engineering, 2023, 51 (9): 2087-2091, 2102.
10	HUANG Z, XU W, YU K. Bidirectional LSTM-CRF models for sequence tagging[EB/OL]. [2024-09-01]. http://de.arxiv.org/pdf/1508.01991.
11	MA X Z, HOVY E. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/1603.01354.
12	陈鹏, 马洪彬, 周佳伦, 等. FCG-NNER: 一种融合字形信息的中文嵌套命名实体识别方法. 重庆理工大学学报(自然科学), 2023, 37 (12): 222- 231.
	CHEN P , MA H B , ZHOU G L , et al. FCG-NNER: a Chinese nested named entity recognition method fused with glyph information. Journal of Chongqing University of Technology (Natural Science), 2023, 37 (12): 222- 231.
13	许力, 李建华. 基于BERT和BiLSTM-CRF的生物医学命名实体识别. 计算机工程与科学, 2021, 43 (10): 1873- 1879.
	XU L , LI J H . Biomedical named entity recognition based on BERT and BiLSTM-CRF. Computer Engineering and Science, 2021, 43 (10): 1873- 1879.
14	VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2016: 3630-3638.
15	SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2017: 4080-4090.
16	MA T T, JIANG H Q, WU Q H, et al. Decomposed meta-learning for few-shot named entity recognition[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2204.05751.
17	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/1703.03400.
18	WANG J N, WANG C Y, TAN C Q, et al. SpanProto: a two-stage span-based prototypical network for few-shot named entity recognition[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. San Diego, USA: Association for Computational Linguistics, 2022: 3466-3476.
19	LI X L, LIANG P. Prefix-Tuning: optimizing continuous prompts for generation[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2101.00190.
20	LAYEGH A, PAYBERAH A H, SOYLU A, et al. ContrastNER: contrastive-based prompt tuning for few-shot NER[C]//Proceedings of the 47th Annual Computers, Software, and Applications Conference. Washington D. C., USA: IEEE Press, 2023: 241-249.
21	ASHOK D, LIPTON Z C. PromptNER: prompt for named entity recognition[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2305.15444.
22	MA R T, ZHOU X, GUI T, et al. Template-free prompt tuning for few-shot NER[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2109.13532.
23	DAS S S S, KATIYAR A, PASSONNEAU R J, et al. CONTaiNER: few-shot named entity recognition via contrastive learning[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2109.07589.
24	LI Y Q, YU Y, QIAN T Y. Type-aware decomposed framework for few-shot named entity recognition[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2302.06397.
25	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/1810.04805.
26	DOZAT T, MANNING C D. Deep biaffine attention for neural dependency parsing[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/1611.01734.
27	YU J T, BOHNET B, POESIO M. Named entity recognition as dependency parsing[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2005.07150.
28	DING N, XU G W, CHEN Y L, et al. Few-NERD: a few-shot named entity recognition dataset[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2105.07464.
29	ZELDES A . The GUM corpus: creating multilayer resources in the classroom. Language Resources and Evaluation, 2017, 51 (3): 581- 612. doi: 10.1007/s10579-016-9343-x
30	PRADHAN S, MOSCHITTI A, XUE N W, et al. Towards robust linguistic analysis using OntoNotes[C]//Proceedings of the 17th Conference on Computational Natural Language Learning. San Diego, USA: Association for Computational Linguistics, 2013: 143-152.
31	ERIK F, SANG T K. Introduction to the CoNLL-2003 shared task: language-independent named entity recognition[C]//Proceedings of the 17th Conference on Natural Language Learning. San Diego, USA: Association for Computational Linguistics, 2003: 142-147.
32	DERCZYNSKI L, NICHOLS E, VAN ERP M, et al. Results of the WNUT2017 shared task on novel and emerging entity recognition[C]//Proceedings of the 3rd Workshop on Noisy User-generated Text. San Diego, USA: Association for Computational Linguistics, 2017: 140-147.
33	YANG Y, KATIYAR A. Simple and effective few-shot named entity recognition with structured nearest neighbor learning[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2010.02405.
34	WANG P Y, XU R X, LIU T Y, et al. An enhanced span-based decomposition method for few-shot sequence labeling[EB/OL]. [2024-09-01]. https://arxiv.org/pdf/2109.13023.
35	HOU Y T, CHE W X, LAI Y K, et al. Few-shot slot tagging with collapsed dependency transfer and label-enhanced task-adaptive projection network[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. San Diego, USA: Association for Computational Linguistics, 2020: 1381-1393.

[1]	YANG Li, CHEN Yanping, HUANG Hui, HUANG Ruizhang, QIN Yongbin. A Named Entity Recognition Method Based on Semantic Plane Interpolation [J]. Computer Engineering, 2026, 52(9): 92-101.
[2]	YANG Xinyi, HE Xiaohai, TENG Qizhi, CHEN Honggang, QING Linbo, WU Xiaohong. Cross-Modal Named Entity Recognition Based on Semantic Fusion [J]. Computer Engineering, 2026, 52(7): 345-353.
[3]	XIE Binhong, SHI Yufei, ZHANG Rui, ZHANG Yingjun. Few-shot Object Detection Method Based on Query Guidance and Semantic Enhancement [J]. Computer Engineering, 2026, 52(3): 141-151.
[4]	WEN Lang, GOU Guanglei, BAI Ruifeng, MIAO Wanyu. Few-shot Fine-grained Image Classification Based on Neighborhood Fusion and Feature Enhancement [J]. Computer Engineering, 2026, 52(2): 158-166.
[5]	LI Xiaoyu, LUO Na. Few-Shot Learning Method with Augmentation Data Based on Transferring Intra-Class Variations [J]. Computer Engineering, 2025, 51(9): 242-251.
[6]	LU Xuan, JING Luqi, PENG Furong. Colorectal Polyp Segmentation Method Based on Incremental Learning [J]. Computer Engineering, 2025, 51(7): 284-293.
[7]	ZHANG Heping, FANG Zhijun, LU Junxin, GAO Yongbin. Few-Shot Relation Classification Based on Knowledge-Enhanced Adaptive Prototype Networks [J]. Computer Engineering, 2025, 51(4): 129-136.
[8]	YANG Junhui, LI Sujin. Chinese Named Entity Recognition Integrating Positional and Entity Category Information [J]. Computer Engineering, 2025, 51(3): 113-121.
[9]	WANG Yuehao, ZHOU Ruohua. Review of Research on Keyword Spotting in Low-Resource Environments [J]. Computer Engineering, 2025, 51(2): 35-53.
[10]	BI Ran, YANG Fengyi, ZHOU Xi, YANG Yating, Abibulla Atawulla. Few-Shot Joint Recognition Method of Intent and Slot Based on Cloze [J]. Computer Engineering, 2025, 51(10): 79-86.
[11]	SI Mingyue, QI Bin, ZHANG Wensheng, ZHANG Lei. Multi-Dimensional Data Calculation and Few-Shot Learning for Intelligent Transportation Based on Tensor Calculation [J]. Computer Engineering, 2024, 50(4): 41-49.
[12]	Haoxin LIU, Chao DONG, Zhinan GOU, Kai GAO. Few-Shot Relation Extraction Method Fusing with Hybrid Representation [J]. Computer Engineering, 2023, 49(8): 63-68.
[13]	Yanyan YANG, Mingxuan XIE, Jiangxia CAO, Xuebin WANG, Tingwen LIU, Yanhui DU. Adversarial Sample Generation for Chinese Classification Model Based on Prototypical Network [J]. Computer Engineering, 2023, 49(8): 54-62.
[14]	Jinshuo LIU, Daichen WANG, Juan DENG, Lina WANG. Classification of Harmful Information on Internet Based on Long-Tailed Classification Algorithm [J]. Computer Engineering, 2023, 49(8): 13-19, 28.
[15]	Yuyan WANG, Jiapeng ZHAO, Jinqiao SHI, Liyan SHEN, Hongmeng LIU, Yanyan YANG. User Identity Information Aggregation Method for Darknet Web Page [J]. Computer Engineering, 2023, 49(11): 187-194, 210.

Please choose a citation manager

Content to export