Similar articles

Abstract: Accurate Chinese named entity recognition (NER) in the process industry is crucial for applications such as information extraction, knowledge graph construction, and intelligent decision-making. However, challenges, including ambiguous entity boundaries, semantic overlaps, and limited annotated data, significantly hinder performance. To address these issues, this study proposes DDiNER, a domain dictionary-guided Chinese NER framework that integrates a hierarchical industrial domain dictionary with bidirectional encoder representations from Transformers (BERT) via a hierarchical lexicon adapter (HLA), combined with bidirectional long short-term memory (BiLSTM) and conditional random field (CRF) layers for multilevel feature fusion. Experimental results show that DDiNER achieves superior performance, with average precision, recall, and F1-scores of 95.75%, 95.73%, and 95.74%, respectively, outperforming state-of-the-art models. Validation on an independent dataset confirms its robustness and strong capability in recognizing unseen and long-tail entities. This study provides an effective and scalable solution for industrial Chinese NER, with significant potential for downstream intelligent applications.

DDiNER：面向复杂工业场景的领域词典引导中文命名实体识别方法

[1]An Y, Xia XY, Chen XL, et al., 2022. Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF. Artif Intell Med, 127:102282.

[2]Ashok D, Lipton ZC, 2023. PromptNER: prompting for named entity recognition.

[3]Chen JW, Lu YJ, Lin HY, et al., 2023. Learning in-context learning for named entity recognition. Proc 61^st Annual Meeting of the Association for Computational Linguistics, p.13661-13675.

[4]Collobert R, Weston J, Bottou L, et al., 2011. Natural language processing (almost) from scratch. J Mach Learn Res, 12:2493-2537.

[5]De S, Sanyal DK, Mukherjee I, 2025. Fine-tuned encoder models with data augmentation beat ChatGPT in agricultural named entity recognition and relation extraction. Expert Syst Appl, 277:127126.

[6]Devlin J, Chang MW, Lee K, et al., 2019. BERT: pre-training of deep bidirectional Transformers for language understanding. Proc Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p.4171-4186.

[7]Ehrmann M, Hamdi A, Pontes EL, et al., 2024. Named entity recognition and classification in historical documents: a survey. ACM Comput Surv, 56(2):1-47.

[8]G V, Kanjirangat V, Gupta D, 2023. AGRONER: an unsupervised agriculture named entity recognition using weighted distributional semantic model. Expert Syst Appl, 229:120440.

[9]Gao C, Zhang X, Han MT, et al., 2021. A review on cyber security named entity recognition. Front Inform Technol Electron Eng, 22(9):1153-1168.

[10]Geng RS, Chen YP, Huang RZ, et al., 2023. Planarized sentence representation for nested named entity recognition. Inform Process Manag, 60(4):103352.

[11]Gong S, Xiong X, Liu YF, et al., 2022. A Transformer-based longer entity attention model for Chinese named entity recognition in aerospace. 5^th Int Conf on Advanced Electronic Materials, Computers and Software Engineering, p.348-355.

[12]Hu Y, Chen QY, Du JC, et al., 2024. Improving large language models for clinical named entity recognition via prompt engineering. J Am Med Inform Assn, 31(9):1812-1820.

[13]Hu Z, Ma XN, 2023. A novel neural network model fusion approach for improving medical named entity recognition in online health expert question-answering services. Expert Syst Appl, 223:119880.

[14]Hu ZT, Hou W, Liu XX, 2024. Deep learning for named entity recognition: a survey. Neur Comput Appl, 36(16):8995-9022.

[15]Ji ZC, Xiao YL, 2024. LLET: lightweight lexicon-enhanced Transformer for Chinese NER. IEEE Int Conf on Acoustics, Speech and Signal Processing, p.12677-12681.

[16]Kumar A, Starly B, 2022. “FabNER”: information extraction from manufacturing process science domain literature using named entity recognition. J Intell Manuf, 33(8):2393-2407.

[17]Li WG, Ramos RM, Brom PC, et al., 2025. Threshold study for Hanzi image recognition: defining character and component limits in Chinese, Japanese, and Korean script processing. Int J Asian Lang Process, 35(1):2450011.

[18]Li XN, Yan H, Qiu XP, et al., 2020. FLAT: Chinese NER using flat-lattice Transformer. Proc 58^th Annual Meeting of the Association for Computational Linguistics, p.6836-6842.

[19]Li ZZ, Feng DW, Li DS, et al., 2020. Learning to select pseudo labels: a semi-supervised method for named entity recognition. Front Inform Technol Electron Eng, 21(6):903-916.

[20]Liu C, Yang SW, 2022. Using text mining to establish knowledge graph from accident/incident reports in risk assessment. Expert Syst Appl, 207:117991.

[21]Liu P, Guo YM, Wang FL, et al., 2022. Chinese named entity recognition: the state of the art. Neurocomputing, 473:37-53.

[22]Liu W, Fu XY, Zhang Y, et al., 2021. Lexicon enhanced Chinese sequence labeling using BERT adapter. Proc 59^th Annual Meeting of the Association for Computational Linguistics and the 11^th Int Joint Conf on Natural Language Processing, p.5847-5858.

[23]Liu YH, Ott M, Goyal N, et al., 2019. RoBERTa: a robustly optimized BERT pretraining approach.

[24]Lu QH, Li R, Wen A, et al., 2025. Large language models struggle in token-level clinical named entity recognition. AMIA Annu Symp Proc, 2024:748-757.

[25]Ma RT, Peng ML, Zhang Q, et al., 2020. Simplify the usage of lexicon in Chinese NER. Proc 58^th Annual Meeting of the Association for Computational Linguistics, p.5951-5960.

[26]McCallum A, Li W, 2003. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. Proc 7^th Conf on Natural Language Learning at HLT-NAACL, p.188-191.

[27]Niu PY, Hou C, 2024. Named entity recognition in Chinese rice breeding questions based on text data augmentation. Trans Chin Soc Agri Mach, 55(8):333-343 (in Chinese).

[28]Prasanna KSL, Lokesh S, Chandramouli G, et al., 2024. BERT-QA: empowering intelligent question answering with NLP and entity recognition. 3^rd Int Conf on Applied Artificial Intelligence and Computing, p.1006-1010.

[29]Qin H, Li M, Wang L, et al., 2025. A radical-based token representation method for enhancing Chinese pre-trained language models. Electronics, 14(5):1031.

[30]Qiu QJ, Tian M, Huang Z, et al., 2024. Chinese engineering geological named entity recognition by fusing multi-features and data enhancement using deep learning. Expert Syst Appl, 238:121925.

[31]Qu XY, Gu YJ, Xia QR, et al., 2024. A survey on Arabic named entity recognition: past, recent advances, and future trends. IEEE Trans Knowl Data Eng, 36(3):943-959.

[32]Seow WL, Chaturvedi I, Hogarth A, et al., 2025. A review of named entity recognition: from learning methods to modelling paradigms and tasks. Artif Intell Rev, 58(10):315.

[33]Sun ZJ, Li XY, Sun XF, et al., 2021. ChineseBERT: Chinese pretraining enhanced by glyph and pinyin information. Proc 59^th Annual Meeting of the Association for Computational Linguistics and the 11^th Int Joint Conf on Natural Language Processing, p.2065-2075.

[34]Wang SH, Sun XF, Li XY, et al., 2023. GPT-NER: named entity recognition via large language models. Findings of the Association for Computational Linguistics: NAACL 2025, p.4257-4275.

[35]Wang XZ, Li JH, Zheng Z, et al., 2022. Entity and relation extraction with rule-guided dictionary as domain knowledge. Front Eng Manag, 9(4):610-622.

[36]Wang ZH, Chen HR, Xu G, et al., 2025. A novel large-language-model-driven framework for named entity recognition. Inform Process Manag, 62(3):104054.

[37]Weigang L, Marinho MC, Li DL, et al., 2024. Six-writings multimodal processing with pictophonetic coding to enhance Chinese language models. Front Inform Technol Electron Eng, 25(1):84-105.

[38]Xuan ZY, Bao R, Jiang SY, 2021. FGN: fusion glyph network for Chinese named entity recognition. Proc 5^th China Conf on Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence, p.28-40.

[39]Yang K, Yang ZW, Zhao SW, et al., 2024. Uncertainty-aware contrastive learning for semi-supervised named entity recognition. Knowl-Based Syst, 296:111762.

[40]Yu YQ, Wang YZ, Mu JQ, et al., 2022. Chinese mineral named entity recognition based on BERT model. Expert Syst Appl, 206:117727.

[41]Zhang H, Wang XY, Liu JX, et al., 2023. Chinese named entity recognition method for the finance domain based on enhanced features and pretrained language models. Inform Sci, 625:385-400.

[42]Zhang H, Dang YP, Zhang YZ, et al., 2024. Chinese nested entity recognition method for the finance domain based on heterogeneous graph network. Inform Process Manag, 61(5):103812.

[43]Zhong L, Wu J, Li Q, et al., 2024. A comprehensive survey on automatic knowledge graph construction. ACM Comput Surv, 56(4):94.

[44]Zhou JY, Ma ZL, 2025. Named entity recognition for construction documents based on fine-tuning of large language models with low-quality datasets. Autom Constr, 174:106151.

[45]Zhou WX, Zhang S, Gu Y, et al., 2023. UniversalNER: targeted distillation from large language models for open named entity recognition.