融合多级别粒度特征的中文医疗命名实体识别

doi:10.19678/j.issn.1000-3428.0070675

摘要/Abstract

摘要： 中文医疗命名实体识别(NER)旨在从医疗文本中识别具有特定意义的实体,如疾病、药物、症状及身体部位等多种类型的医疗实体。这一任务可为临床辅助决策、医疗信息整合和病案管理等方面提供有力支持。现有的中文医疗NER研究尚未充分考虑医疗文本的复杂结构,存在专业术语繁多、嵌入信息单一、语义信息利用不足等问题。为此,提出一种融合多级别粒度特征的中文医疗文本NER模型。该模型首先利用BERT预训练模型生成文本的字嵌入表示,并设计了一维和二维卷积神经网络(CNN)提取字符的字形与笔画特征,同时通过外部词库引入词级特征,以增强对词与实体边界的信息表达。此外,模型还加入句子级特征以捕获全局语义特征。通过交叉注意力机制将上述多级别的粒度特征进行迭代融合,得到包含深层语义信息的嵌入表示,最后利用条件随机场(CRF)输出实体识别结果。在CCKS2017和CCKS2019数据集上的实验结果表明,该模型F1值达到92.88%和87.86%,相较于当前主流模型展现了更优异的识别性能。

关键词: 命名实体识别, 医疗文本, 特征融合, 特征增强, 交叉注意力

Abstract: Chinese medical Named Entity Recognition (NER) aims to identify entities with specific meanings from medical texts, such as diseases, drugs, symptoms, and anatomical parts. This task provides robust support for clinical decision making, medical information integration, and medical record management. However, existing research on Chinese medical NER has not fully addressed the complexity of medical texts, which are characterized by an abundance of specialized terminology, limited embedding diversity, and insufficient utilization of semantic information. To address these issues, this paper proposes a Chinese medical NER model that integrates multigranularity features. The model first employs a BERT pretrained model to generate character embeddings for the text. It then uses both one-dimensional and two-dimensional convolutional neural networks to extract character shape and stroke features, while external lexicons are incorporated to introduce word-level features, enhancing the representation of word and entity boundaries. Additionally, sentence-level features are included to capture global semantic information. A cross-attention mechanism is utilized to iteratively fuse these multigranular features, resulting in embeddings enriched with deep semantic information. Finally, Conditional Random Fields (CRF) are used to output the entity recognition results. Experimental results on the CCKS2017 and CCKS2019 datasets demonstrate that the proposed model achieves F1 values of 92.88% and 87.86%, respectively, outperforming mainstream models in recognition performance.

Key words: Named Entity Recognition(NER), medical text, feature fusion, feature enhancement, cross-attention

中图分类号:

TP391

代子男, 张捷, 陈冲冲, 谌章义, 陈付龙. 融合多级别粒度特征的中文医疗命名实体识别[J]. 计算机工程, 2026, 52(10): 154-163.

DAI Zinan, ZHANG Jie, CHEN Chongchong, CHEN Zhangyi, CHEN Fulong. Chinese Medical Named Entity Recognition Integrating Multi-Level Granular Features[J]. Computer Engineering, 2026, 52(10): 154-163.

https://www.ecice06.com/CN/Y2026/V52/I10/154

参考文献

[1] KE J, WANG W J, CHEN X J, et al. Medical entity recognition and knowledge map relationship analysis of Chinese EMRs based on improved BiLSTM-CRF[J]. Computers and Electrical Engineering, 2023, 108: 108709.
[2] YI F, LIU H, WANG Y, et al. Medical named entity recognition fusing part-of-speech and stroke features[J]. Applied Sciences, 2023, 13(15): 8913.
[3] 赵继贵, 钱育蓉, 王魁, 等. 中文命名实体识别研究综述[J]. 计算机工程与应用, 2024, 60(1): 15-27. ZHAO J G, QIAN Y R, WANG K, et al. Survey of Chinese named entity recognition research[J]. Computer Engineering and Applications, 2024, 60(1): 15-27. (in Chinese)
[4] 崔博文, 金涛, 王建民. 自由文本电子病历信息抽取综述[J]. 计算机应用, 2021, 41(4): 1055-1063. CUI B W, JIN T, WANG J M. Overview of information extraction of free-text electronic medical records[J]. Journal of Computer Applications, 2021, 41(4): 1055-1063. (in Chinese)
[5] LAFFERTY J D, MCCALLUM, A, PEREIRA F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning. San Francisco, USA: Morgan Kaufmann Publishers Inc, 2001: 282-289.
[6] NOBLE W S. What is a support vector machine?[J]. Nature Biotechnology, 2006, 24(12): 1565-1567.
[7] SAMPATHKUMAR H, CHEN X W, LUO B. Mining adverse drug reactions from online healthcare forums using hidden Markov model[J]. BMC Medical Informatics and Decision Making, 2014, 14(1): 91.
[8] TRAN Q, MACKINLAY A, YEPES A J. Named entity recognition with stack residual LSTM and trainable bias decoding[EB/OL].[2025-01-23]. https://arxiv.org/pdf/1706.07598.
[9] HE H, SUN X. A unified model for cross-domain and semi-supervised named entity recognition in chinese social media[C]//Proceedings of the AAAI conference on artificial intelligence. San Francisco, California, USA : AAAI Press, 2017: 3216-3222.
[10] SCHUSTER M, PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681.
[11] XU K, ZHOU Z F, HAO T Y, et al. A bidirectional LSTM and conditional random fields approach to medical named entity recognition[C]//Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2017. Berlin, Germany: Springer, 2017: 355-365.
[12] 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[J]. 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[J]. Opto-Electronic Engineering, 2024, 51(5): 240034. (in Chinese)
[13] YIN M W, MOU C J, XIONG K N, et al. Chinese clinical named entity recognition with radical-level feature and self-attention mechanism[J]. Journal of Biomedical Informatics, 2019, 98: 103289.
[14] ZHANG Y, YANG J. Chinese NER using lattice LSTM[EB/OL]. [2025-01-23]. https://arxiv.org/pdf/1805.02023.
[15] MA R T, PENG M L, ZHANG Q, et al. Simplify the usage of lexicon in Chinese NER[EB/OL]. [2025-01-23]. http://arxiv.org/pdf/1908.05969.
[16] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL]. [2025-01-23]. https://arxiv.org/pdf/1810.04805.
[17] LIU W, FU X Y, ZHANG Y, et al. Lexicon enhanced Chinese sequence labeling using BERT adapter[EB/OL]. [2025-01-23]. https://arxiv.org/pdf/2105.07148.
[18] 罗凌, 杨志豪, 宋雅文, 等. 基于笔画ELMo和多任务学习的中文电子病历命名实体识别研究[J]. 计算机学报, 2020, 43(10): 1943-1957. LUO L, YANG Z H, SONG Y W, et al. Chinese clinical named entity recognition based on stroke ELMo and multi-task learning[J]. Chinese Journal of Computers, 2020, 43(10): 1943-1957. (in Chinese)
[19] 宋雅文,杨志豪,罗凌, 等. 基于字符卷积神经网络的生物医学变异实体识别方法[J]. 中文信息学报, 2021, 35(5): 63-69. SONG Y W, YANG Z H, LUO L, et al. Biomedical mutation entity recognition method based on character convolution neural network[J]. Journal of Chinese Information Processing, 2021, 35(5): 63-69.(in Chinese)
[20] LI Y B, WANG X H, HUI L H, et al. Chinese clinical named entity recognition in electronic medical records: development of a lattice long short-term memory model with contextualized character representations[J]. JMIR Medical Informatics, 2020, 8(9): e19848.
[21] WANG Q C, HAIHONG E. A BERT-based named entity recognition in Chinese electronic medical record[C]//Proceedings of the 20209th International Conference on Computing and Pattern Recognition. New York, USA: ACM Press, 2020: 13-17.
[22] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2025-01-23]. https://export.arxiv.org/pdf/1301.3781.
[23] PENNINGTON J, SOCHER R, MANNING C. GloVe: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, USA: ACL, 2014: 1532-1543.
[24] LI F, WANG Z, HUI S C, et al. Modularized interaction network for named entity recognition[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2021: 200-209.
[25] SHI J T, SUN M X, SUN Z Y, et al. Multi-level semantic fusion network for Chinese medical named entity recognition[J]. Journal of Biomedical Informatics, 2022, 133: 104144.
[26] AN Y, XIA X Y, CHEN X L, et al. Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF[J]. Artificial Intelligence in Medicine, 2022, 127: 102282.
[27] 唐卓然, 柳毅. 基于词汇融合和依存关系的中文命名实体识别[J]. 计算机工程, 2024, 50(10): 145-153. TANG Z R, LIU Y. Chinese named entity recognition based on lexicon fusion and dependency relation[J]. Computer Engineering, 2024, 50(10): 145-153. (in Chinese)
[28] 林令德, 刘纳, 徐贞顺, 等. 基于多层动态融合的中文医疗命名实体识别[J]. 计算机工程与应用, 2024, 60(15): 161-169. LIN L D, LIU N, XU Z S, et al. Chinese medical named entity recognition based on multi-layer dynamic fusion[J]. Computer Engineering and Applications, 2024, 60(15): 161-169. (in Chinese)
[29] LI X N, YAN H, QIU X P, et al. FLAT: Chinese NER using flat-lattice transformer[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2020: 6836-6842.
[30] 乔锐, 杨笑然,黄文亢.基于BERT与模型融合的医疗命名实体识别[C]//全国知识图谱与语义计算会议评估任务论文集.杭州, 中国:[s.n],2019:1-6. QIAO R, YANG X R, HUANG W K. Medical named entity recognition based on BERT and model fusion[C]//Proceedings of Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing. Hangzhou, China:[s. n], 2019:1-6.(in Chinese)
[31] 陈明, 刘蓉, 张晔. 基于多重注意力机制的中文医疗实体识别[J]. 计算机工程, 2023, 49(6): 314-320. CHEN M, LIU R, ZHANG Y. Chinese medical entity recognition based on multiple attention mechanism[J]. Computer Engineering, 2023, 49(6): 314-320. (in Chinese)
[32] WANG C Y, WANG H, ZHUANG H, et al. Chinese medical named entity recognition based on multi-granularity semantic dictionary and multimodal tree[J]. Journal of Biomedical Informatics, 2020, 111: 103583.
[33] WU S, SONG X N, FENG Z H. MECT: multi-metadata embedding based cross-transformer for Chinese named entity recognition[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2021: 1529-1539.
[34] 陆鑫涛, 孙丽萍, 凌晨, 等. 融入拼音与词性特征的中文电子病历命名实体识别[J]. 小型微型计算机系统, 2025, 46(2): 330-338. LU X T, SUN L P, LING C, et al. Named entity recognition of Chinese electronic health records incorporating phonetic and part-of-speech features[J]. Journal of Chinese Computer Systems, 2025, 46(2): 330-338. (in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容