融合词汇增强和跨度方法的中医药命名实体识别

doi:10.3778/j.issn.1002-8331.2405-0169

摘要/Abstract

摘要： 中医药命名实体识别旨在从非结构化的中医药文本中识别出相应的实体及其类别，采用人工识别效率不高。然而，传统的中文命名实体识别模型缺少中医药文本中的特征信息且一般采用序列标注方式解码，无法解决中医药实体识别中突出存在的实体边界识别模糊和实体嵌套性错误等问题。为解决上述问题，提出融合词汇增强与跨度方法的中医药命名实体识别模型TCM-NER来提升实体识别性能。根据词汇匹配获得文本中的词汇信息并利用相对位置构建中医药文本词格结构；通过特征提取模块分别提取字、词汇和相对位置编码向量；采用FLAT（flat-lattice Transformer）模型进行特征整合，从而获得<字-词汇-跨度>混合特征，提高模型边界识别性能；将混合特征输入双仿射分类器预测实体及其类别。实验结果表明，TCM-NER模型在两个中医药数据集的Micro-F1值分别达到了70.53%和75.91%，证明了该模型在中医药实体识别中的实用价值。

关键词: 词汇增强, 跨度方法, 命名实体识别, 中医药（TCM）, 双仿射分类器

Abstract: Named entity recognition (NER) for traditional Chinese medicine (TCM) aims to identify corresponding entities and their categories from unstructured text, a task that is inefficient when manually performed. However, conventional Chinese named entity recognition models lack the feature information in TCM text and often use sequence annotation for decoding, which is unable to address prominent issues in recognizing TCM entities, such as ambiguous entity boundary recognition and nested entity recognition. To solve the above problems, a novel method with lexical enhancement and span method is proposed to enhance entity recognition performance, which is named TCM-NER. Firstly, the lexical information in the text is obtained according to lexical matching and the relative location information is used to construct the flat-lattice structure for TCM text. Secondly, character-level embedding, lexical-level embedding and relative position coding embedding are extracted by the feature extraction module. Thirdly, a FLAT (flat-lattice Transformer) model is used to integrate the features, which obtains the <character-lexical-span> fusion feature, thereby improving the boundary recognition performance. Finally, the fusion feature is input into a biaffine classifier to predict the entity and its categories. Experimental results on two datasets indicate that TCM-NER model gets Micro-F1 scores of 70.53% and 75.91%, demonstrating its practical value in the recognition of TCM entities.

Key words: lexical enhancement, span method, named entity recognition, traditional Chinese medicine(TCM), biaffine classifier

叶青, 赖煊, 程春雷, 杨琴. 融合词汇增强和跨度方法的中医药命名实体识别[J]. 计算机工程与应用, 2025, 61(17): 222-231.

YE Qing, LAI Xuan, CHENG Chunlei, YANG Qin. Named Entity Recognition for Traditional Chinese Medicine with Lexical Enhancement and Span Method[J]. Computer Engineering and Applications, 2025, 61(17): 222-231.

参考文献

[1] EL-SHAFAI W, MAHMOUD A A, EL-RABAIE E M, et al. Traditional Chinese medicine automated diagnosis based on knowledge graph reasoning[J]. Computers, Materials & Continua, 2022, 71(1): 159-170.
[2] 沈蓉蓉, 夏帅帅, 晏峻峰. 命名实体识别在中医药领域研究进展[J]. 医学信息学杂志, 2023, 44(1): 47-53.
SHEN R R, XIA S S, YAN J F. Research progress of named entity recognition in traditional Chinese medicine[J]. Journal of Medical Informatics, 2023, 44(1): 47-53.
[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.
[4] ZHANG Y, YANG J. Chinese NER using lattice LSTM[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2018: 1554-1564.
[5] 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: ACL, 2020: 6836-6842.
[6] 李莉, 奚雪峰, 盛胜利, 等. 深度学习中文命名实体识别研究进展[J]. 计算机工程与应用, 2023, 59(24): 46-69.
LI L, XI X F, SHENG S L, et al. Research progress on named entity recognition in Chinese deep learning[J]. Computer Engineering and Applications, 2023, 59(24): 46-69.
[7] 肖瑞, 胡冯菊, 裴卫. 基于BiLSTM-CRF的中医文本命名实体识别[J]. 世界科学技术-中医药现代化, 2020, 22(7): 2504-2510.
XIAO R, HU F J, PEI W. Chinese medicine text named entity recognition based on BiLSTM-CRF[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2020, 22(7): 2504-2510.
[8] 胡为, 刘伟, 石玉敬. 基于BERT-BiLSTM-CRF的中医医案命名实体识别方法[J]. 计算机时代, 2022(9): 119-122.
HU W, LIU W, SHI Y J. Named entity recognition of TCM medical records based on BERT-BiLSTM-CRF[J]. Computer Era, 2022(9): 119-122.
[9] 徐丽娜, 李燕, 钟昕妤, 等. 基于BERT的中医方剂文本命名实体识别[J]. 医学信息, 2023, 36(4): 32-37.
XU L N, LI Y, ZHONG X Y, et al. Named entity recognition of traditional Chinese medicine prescription based on BERT[J]. Journal of Medical Information, 2023, 36(4): 32-37.
[10] CHO M, HA J, PARK C, et al. Combinatorial feature embedding based on CNN and LSTM for biomedical named entity recognition[J]. Journal of Biomedical Informatics, 2020, 103: 103381.
[11] 刘歆宁. 融合多特征及协同注意力的医学命名实体识别[J]. 计算机工程与应用, 2024, 60(6): 188-198.
LIU X N. Medical named entity recognition based on multi-feature and co-attention[J]. Computer Engineering and Applications, 2024, 60(6): 188-198.
[12] 罗熹, 夏先运, 安莹, 等. 结合多头自注意力机制与BiLSTM-CRF的中文临床实体识别[J]. 湖南大学学报(自然科学版), 2021, 48(4): 45-55.
LUO X, XIA X Y, AN Y, et al. Chinese CNER combined with multi-head self-attention and BiLSTM-CRF[J]. Journal of Hunan University (Natural Sciences), 2021, 48(4): 45-55.
[13] SUI D B, CHEN Y B, LIU K, et al. Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 3828-3838.
[14] SONG C J, XIONG Y, HUANG W C, et al. Joint self-attention and multi-embeddings for Chinese named entity recognition[C]//Proceedings of the 6th International Conference on Big Data Computing and Communications. Piscataway: IEEE, 2020: 76-80.
[15] 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: ACL, 2021: 1529-1539.
[16] MA R T, PENG M L, ZHANG Q, et al. Simplify the usage of lexicon in Chinese NER[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 5951-5960.
[17] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the Neural Information Processing Systems, 2017: 6000-6010.
[18] YAN H, DENG B, LI X, et al. TENER: adapting transformer encoder for named entity recognition[J]. arXiv:1911.04474, 2019.
[19] DOZAT T, MANNING C. Deep biaffine attention for neural dependency parsing[J]. arXiv:1611.01734, 2016.
[20] 李冀. 方剂学[M]. 北京: 中国中医药出版社, 2016.
LI J. Pharmacology of traditional Chinese medical formulae[M]. Beijing: China Press of Traditional Chinese Medicine, 2016.
[21] DENG N, FU H, CHEN X. Named entity recognition of traditional Chinese medicine patents based on BiLSTM-CRF[J]. Wireless Communications and Mobile Computing, 2021, 2021: 6696205.
[22] 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.
[23] LIU W, XU T, XU Q, et al. An encoding strategy based word-character LSTM for Chinese NER[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 2379-2389.
[24] GUI T, MA R T, ZHANG Q, et al. CNN-based Chinese NER with lexicon rethinking[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2021: 4982-4988.
[25] SU J L, MURTADHA A, PAN S F, et al. Global pointer: novel efficient span-based approach for named entity recognition[J]. arXiv:2208.03054, 2022.
[26] ZHANG N Y, CHEN M S, BI Z, et al. CBLUE: a Chinese biomedical language understanding evaluation benchmark[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2022: 7888-7915.
[27] WANG Y C, YU B W, ZHANG Y Y, et al. TPLinker: single-stage joint extraction of entities and relations through token pair linking[C]//Proceedings of the 28th International Conference on Computational Linguistics. 2020: 1572-1582.
[28] LI X Y, FENG J R, MENG Y X, et al. A unified MRC framework for named entity recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 5849-5859.