·1196 工程科学学报，第43卷.第9期 [8]Lei J,Tang B,Lu X,et al.A comprehensive study of named entity [18]Wei Q K,Chen T,Xu R F,et al.Disease named entity recognition recognition in Chinese clinical text.JAm Med Inform Assoc,2014 by combining conditional random fields and bidirectional recurrent 21(5):808 neural networks.Database (Oxford),2016,140:1 [9]Hirschberg J,Manning C D.Advances in natural language [19]Gong L J,Zhang Z F.Clinical named entity recognition from processing.Science,2015,349(6245):261 Chinese electronic medical records using a double-layer annotation [10]Wang Q,Zhou Y M,Ruan T,et al.Incorporating dictionaries into model combining a domain dictionary with CRF.Chin J Eng, deep neural networks for the Chinese clinical named entity 2020,42(4):469 recognition.J Biomed Informatics,2019,92:103133 (龚乐君，张知菲.基于领域词典与CRF双层标注的中文电子病 [11]Shang J B,Liu L Y,Gu X T,et al.Learning named entity tagger 历实体识别.工程科学学报，2020,42(4)：469) using domain-specific dictionary//Proceedings of the 2018 [20]Hu J L,Shi X,Liu Z J,et al.HITSZ CNER:a hybrid system for Conference on Empirical Methods in Natural Language entity recognition from Chinese clinical text//Proceedings of the Processing.Brussels,2018:2054 Evaluation Tasks at the China Conference on Knowledge Graph [12]Kraus S,Blake C,West S L.Information extraction from medical and Semantic Computing (CCKS 2017).Chengdu,2017:1 notes [J/OL].arXiv preprint (2007-07-24)[2020-12-26].http:// [21]Mikolov T,Grave E,Bojanowski P,et al.Advances in pre-training citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.120.3671&rep distributed word representations [J/OL].arXiv preprint (2017-12- =repl&type=pdf 26)[2020-12-26.https:://arxiv.org/pdi1712.09405.pdf [13]Gorinski P J,Wu HH,Grover C,et al.Named entity recognition [22]Pennington J,Socher R,Manning C.GloVe:global vectors for for electronic health records:A comparison of rule-based and word representation//Proceedings of the 2014 Conference on machine learning approaches [J/OL].arXiy preprint(2019-04-25) Empirical Methods in Natural Language Processing (EMNLP). [2020-12-26].https://arxiv.org/pdf/1903.03985.pdf Doha,2014:1532 [14]Ma X Z,Hovy E.End-to-end Sequence Labeling via Bi-directional [23]Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need LSTM-CNNs-CRF [J/OL].arXiv preprint(2016-05-29)[2020-12- [J/0L.arXiv preprint(2017-12-06)[2020-12-26].htps:/axiv. 26].https://arxiv.org/pdf/1603.01354.pdf org/pd1706.03762.pdf [15]Zhang Y.Yang J.Chinese NER Using Lattice LSTM [J/OL]. [24]Choi E,Bahadori M T,Kulas J A,et al.RETAIN:interpretable arXiv preprint (2018-07-05)[2020-12-26].https://arxiv.org/pdf/ predictive model in healthcare using reverse time attention 1805.02023.pdf mechanism [J/OL].arXiv preprint (2016-08-19)[2020-12-26]. [16]Alsentzer E,Murphy JR,Boag W,et al.Publicly available clinical https://arxiv.org/pdf/1608.05745.pdf BERT embeddings [J/OL].arXiv preprint (2019-6-20)[2020-12- [25]Zhu QL.Li X L,Conesa A,et al.GRAM-CNN:a deep learning 26].https://arxiv.org/pdf/1904.03323.pdf approach with local context for named entity recognition in [17]Jiang M,Chen Y K,Liu M,et al.A study of machine-learning- biomedical text.Bioinformatics,2018,34(9):1547 based approaches to extract clinical entities and their assertions [26]Wu G H,Tang GG,Wang Z R,et al.An attention-based from discharge summaries.JAm Med Inform Assoc,2011,18(5): BiLSTM-CRF model for Chinese clinic named entity recognition. 601 IEEE Access,2019,7:113942Lei J, Tang B, Lu X, et al. A comprehensive study of named entity recognition in Chinese clinical text. J Am Med Inform Assoc, 2014, 21（5）: 808 [8] Hirschberg  J,  Manning  C  D.  Advances  in  natural  language processing. Science, 2015, 349（6245）: 261 [9] Wang Q, Zhou Y M, Ruan T, et al. Incorporating dictionaries into deep  neural  networks  for  the  Chinese  clinical  named  entity recognition. J Biomed Informatics, 2019, 92: 103133 [10] Shang J B, Liu L Y, Gu X T, et al. Learning named entity tagger using  domain-specific  dictionary//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, 2018: 2054 [11] Kraus S, Blake C, West S L. Information extraction from medical notes  [J/OL]. arXiv preprint (2007-07-24)  [2020-12-26]. http:// citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.120.3671&rep =rep1&type=pdf [12] Gorinski P J, Wu H H, Grover C, et al. Named entity recognition for  electronic  health  records:  A  comparison  of  rule-based  and machine learning approaches [J/OL]. arXiv preprint (2019-04-25) [2020-12-26]. https://arxiv.org/pdf/1903.03985.pdf [13] Ma X Z, Hovy E. End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF [J/OL]. arXiv preprint (2016-05-29) [2020-12- 26]. https://arxiv.org/pdf/1603.01354.pdf [14] Zhang  Y,  Yang  J.  Chinese  NER  Using  Lattice  LSTM  [J/OL]. arXiv preprint (2018-07-05)  [2020-12-26]. https://arxiv.org/pdf/ 1805.02023.pdf [15] Alsentzer E, Murphy J R, Boag W, et al. Publicly available clinical BERT  embeddings  [J/OL]. arXiv preprint (2019-6-20)  [2020-12- 26]. https://arxiv.org/pdf/1904.03323.pdf [16] Jiang  M,  Chen  Y  K,  Liu  M,  et  al.  A  study  of  machine-learning￾based  approaches  to  extract  clinical  entities  and  their  assertions from discharge summaries. J Am Med Inform Assoc, 2011, 18（5）: 601 [17] Wei Q K, Chen T, Xu R F, et al. Disease named entity recognition by combining conditional random fields and bidirectional recurrent neural networks. Database (Oxford), 2016, 140: 1 [18] Gong  L  J,  Zhang  Z  F.  Clinical  named  entity  recognition  from Chinese electronic medical records using a double-layer annotation model  combining  a  domain  dictionary  with  CRF. Chin J Eng, 2020, 42（4）: 469 （龚乐君, 张知菲. 基于领域词典与CRF双层标注的中文电子病 历实体识别. 工程科学学报, 2020, 42（4）：469） [19] Hu J L, Shi X, Liu Z J, et al.HITSZ_CNER: a hybrid system for entity  recognition  from  Chinese  clinical  text//Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing (CCKS 2017). Chengdu, 2017: 1 [20] Mikolov T, Grave E, Bojanowski P, et al. Advances in pre-training distributed word representations [J/OL]. arXiv preprint (2017-12- 26) [2020-12-26]. https://arxiv.org/pdf/1712.09405.pdf [21] Pennington  J,  Socher  R,  Manning  C.  GloVe:  global  vectors  for word  representation//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, 2014: 1532 [22] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [J/OL]. arXiv preprint (2017-12-06)  [2020-12-26]. https://arxiv. org/pdf/1706.03762.pdf [23] Choi  E,  Bahadori  M  T,  Kulas  J  A,  et  al.  RETAIN:  interpretable predictive  model  in  healthcare  using  reverse  time  attention mechanism  [J/OL]. arXiv preprint (2016-08-19)  [2020-12-26]. https://arxiv.org/pdf/1608.05745.pdf [24] Zhu Q L, Li X L, Conesa A, et al. GRAM-CNN: a deep learning approach  with  local  context  for  named  entity  recognition  in biomedical text. Bioinformatics, 2018, 34（9）: 1547 [25] Wu  G  H,  Tang  G  G,  Wang  Z  R,  et  al.  An  attention-based BiLSTM-CRF model for Chinese clinic named entity recognition. IEEE Access, 2019, 7: 113942 [26] · 1196 · 工程科学学报，第 43 卷，第 9 期