Please wait a minute...
Advanced Search
数据分析与知识发现  2023, Vol. 7 Issue (2): 26-37     https://doi.org/10.11925/infotech.2096-3467.2022.0908
  专题 本期目录 | 过刊浏览 | 高级检索 |
面向中文医学文本命名实体识别的神经网络模块分解分析*
段宇锋(),贺国秀
华东师范大学经济与管理学部 上海 200062
Analysis of Neural Network Modules for Named Entity Recognition of Chinese Medical Texts
Duan Yufeng(),He Guoxiu
Faculty of Economics and Management, East China Normal University, Shanghai 200062, China
全文: PDF (807 KB)   HTML ( 18
输出: BibTeX | EndNote (RIS)      
摘要 

目的】 对基于神经网络的中文医学文本命名实体识别模型进行分解,研究符号表示层和上下文编码层中基础神经网络模块功能以及多神经网络模块协同组合对实体识别性能的影响。【方法】 基于CCKS2017、CCKS2019和IMCS-NER等中文医学文本命名实体识别任务发布的基准语料,对比分析神经网络模型的符号表示层和上下文编码层采用不同神经网络模块时的性能差异。以此为基础,分别构建将多神经网络模块集成、并联、串联的实体识别模型,比较并分析其性能差异。【结果】 符号表示层使用hfl/chinese-macbert-base、hfl/chinese-roberta-wwm-ext、hfl/chinese-bert-wwm-ext等预训练语言模型能显著提高识别性能,平均F1值分别达到0.881 6、0.881 6、0.881 2;在上下文编码层融合神经网络模块能够提高识别性能。其中,基于集成的神经网络性能最优,F1值分别达到0.933 0、0.821 1、0.918 1。【局限】 实验仅基于中文医学文本语料,所得结论有待在其他语种的语料上进行验证。【结论】 基础神经网络模块的类型和多神经网络模块的协同方式显著影响神经网络在中文医学文本命名实体识别任务上的表现。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
段宇锋
贺国秀
关键词 命名实体识别神经网络模块分解中文医学文本    
Abstract

[Objective] This paper decomposes the named entity recognition models based on neural network for Chinese medical texts. We investigate the impacts of single neural network module and the collaboration of multiple modules on the entity recognition performance. [Methods] First, we chosed the benchmark datasets from CCKS2017, CCKS2019, and IMCS-NER for named entity recognition tasks. Then, we conducted extensive experiments to compare the performance of different single modules of the aforementioned layers. Third, we built and compared entity recognition models based on ensemble, parallel, and serial neural models. [Results] Using hfl/chinese-macbert-base, hfl/chinese-roberta-wwm-ext, hfl/chinese-bert-wwm-ext in the symbolic representation layer significantly improved the performance of entity recognition models, the average F1-scores reached 0.8816, 0.8816 and 0.8812 respectively. Stacking neural models at the context encoding layer improved the performance of the neural network. Moreover, ensembled neural networks could achieve the best performance, the F1-scores reached 0.9330, 0.8211 and 0.9181 respectively. [Limitations] More research is needed to examine our findings with datasets in other languages. [Conclusions] The characteristics of single neural modules and their collaboration could significantly affect the performance of the named entity recognition of Chinese medical texts.

Key wordsNamed Entity Recognition    Neural Network    Module Decomposition    Chinese Medical Text
收稿日期: 2022-08-28      出版日期: 2023-03-28
ZTFLH:  TP391  
基金资助:*国家社会科学基金项目的研究成果之一(20BTQ092)
通讯作者: 段宇锋,ORCID: 0000-0002-4319-2837, E-mail: yfduan@infor.ecnu.edu.cn。   
引用本文:   
段宇锋, 贺国秀. 面向中文医学文本命名实体识别的神经网络模块分解分析*[J]. 数据分析与知识发现, 2023, 7(2): 26-37.
Duan Yufeng, He Guoxiu. Analysis of Neural Network Modules for Named Entity Recognition of Chinese Medical Texts. Data Analysis and Knowledge Discovery, 2023, 7(2): 26-37.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2022.0908      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2023/V7/I2/26
Fig.1  研究方案
Fig.2  神经网络结构
数据集 实体类型和数量 合计
CCKS2017 症状体征
7 831
检查检验
9 546
疾病诊断
722
治疗
1 048
身体部位
10 719
29 866
CCKS2019 疾病和诊断
5 492
影像检查
1 303
实验室检验
1 691
手术
1 182
药物
2 267
解剖部位
11 466
23 401
IMCS-NER 症状
38 993
药品名
14 528
药物类别
6 563
检查
10 738
操作
2 146
72 968
Table 1  语料统计
超参数 基础神经网络模型
(使用静态嵌入表示字向量时)
基础神经网络模型(使用BERT表示字向量时)/
集成结构的模型
并联结构的模型/
串联结构的模型
batch_size 32 32 8, 16, 32, 64
embedding_dim 64, 128, 256, 384, 512, 640, 768 768 768
hidden_size 128 128 32, 64, 128
dropout 0.3 0.3 0.3, 0.4, 0.5
learning_rate 1e-3 1e-5 1e-4, 5e-5, 1e-5
criterion torch.nn.NLLLoss torch.nn.NLLLoss torch.nn.NLLLoss
optimizer torch.optim.Adam torch.optim.AdamW torch.optim.AdamW
Table 2  模型超参数
数据集 Vote Parallel_add Parallel_cat Series LSTM CNN MLP Multihead Self-Attention
CCKS2017 0.933 0 0.932 7 0.931 6 0.929 3 0.926 8 0.929 4 0.928 6 0.922 1
CCKS2019 0.821 1 0.820 2 0.820 2 0.817 8 0.812 8 0.797 8 0.809 0 0.805 0
IMCS-NER 0.918 1 0.914 1 0.915 0 0.913 8 0.911 6 0.910 7 0.912 0 0.908 0
Table 3  多神经网络模块融合模型与基础神经网络模型的比较
数据集 Dim128 Dim256 Dim512 Dim768 bert-base bert-wwm bert-wwm-ext roberta bert-wwm-ehr macbert macbert-med
CCKS2017 0.810 6 0.815 0 0.812 0 0.802 8 0.925 8 0.926 6 0.926 8 0.9277 0.901 2 0.927 6 0.824 0
CCKS2019 0.609 5 0.617 3 0.605 0 0.595 0 0.798 9 0.805 6 0.806 1 0.8057 0.736 9 0.806 4 0.576 4
IMCS-NER 0.784 2 0.781 7 0.772 1 0.758 2 0.911 4 0.909 9 0.910 6 0.9113 0.897 3 0.910 7 0.884 9
Table 4  词嵌入方式对命名实体识别性能(F1值)的影响
数据集 Dim64 Dim128 Dim256 Dim384 Dim512 Dim640 Dim768
CCKS2017 0.906 5 0.913 4 0.916 1 0.918 6 0.918 9 0.918 4 0.919 6
CCKS2019 0.746 5 0.762 3 0.766 5 0.764 1 0.766 0 0.768 2 0.764 0
IMCS-NER 0.893 3 0.895 2 0.893 0 0.893 9 0.891 2 0.890 0 0.888 6
Table 5  嵌入维度对LSTM模型性能(F1值)的影响
LSTM GRU RNN CNN MLP Multihead Self-Attention
No.1频次 4 1 2 2 1
No.2频次 2 2 1 3
No.3频次 3 2 1 3 1
总分 16 10 8 9 12 1
Table 6  模型性能总体评价
模型 I-
Image
B-
Anat
B-
DiSA
B-
OPS
B-
LabInsp
O 合计
LSTM 10 2 2 1 11 26
GRU 10 2 1 1 11 25
RNN 4 2 2 1 13 22
CNN 6 2 1 1 11 21
MLP 2 2 1 1 1 8 15
Self-Attn-MH 5 2 2 1 13 23
Table 7  B-Image标签假正例(FP)的分布
模型 I-
Image
B-Anat B-
DiSA
I-
DiSA
B-OPS B-
LabInsp
O 合计
LSTM 5 4 1 14 24
GRU 6 7 2 15 30
RNN 4 3 1 2 14 24
CNN 6 3 2 1 19 31
MLP 4 4 1 1 9 19
Self-Attn-MH 4 4 1 1 11 21
Table 8  B-Image标签假反例(FN)的分布
[1] 李雯昕, 张坤丽, 关同峰, 等. CHIP2020评测任务1概述:中文医学文本命名实体识别[J]. 中文信息学报, 2022, 36(4): 66-72.
[1] (Li Wenxin, Zhang Kunli, Guan Tongfeng, et al. Overview of CHIP2020 Shared Task 1: Named Entity Recognition in Chinese Medical Text[J]. Journal of Chinese Information Processing, 2022, 36(4): 66-72.)
[2] Yang X, Huang W. A Conditional Random Fields Approach to Clinical Name Entity Recognition[EB/OL]. [2022-08-08]. http://ceur-ws.org/Vol-2242/paper01.pdf.
[3] Tong Y Q, Chen Y D, Shi X D. A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity Information[C]// Proceedings of the 2021 International Joint Conference on Natural Language Processing. 2021: 4804-4813.
[4] Li L Q, Zhao J, Hou L, et al. An Attention-Based Deep Learning Model for Clinical Named Entity Recognition of Chinese Electronic Medical Records[J]. BMC Medical Informatics and Decision Making, 2019, 19(S5): 235.
doi: 10.1186/s12911-019-0933-6
[5] Crichton G, Pyysalo S, Chiu B, et al. A Neural Network Multi-Task Learning Approach to Biomedical Named Entity Recognition[J]. BMC Bioinformatics, 2017, 18(1): 368.
doi: 10.1186/s12859-017-1776-8 pmid: 28810903
[6] 盛羽, 胡慧荣, 王聪聪, 等. 医学影像诊断报告的结构化研究[J]. 数据分析与知识发现, 2022, 6(10): 46-56.
[6] (Sheng Yu, Hu Huirong, Wang Congcong, et al. Analyzing Structures of Medical Imaging Diagnosis Reports[J]. Data Analysis and Knowledge Discovery, 2022, 6(10): 46-56.)
[7] 颜柏杨, 吴陈. 基于自注意力机制的中文医疗命名实体识别[J]. 计算机与数字工程, 2022, 50(4): 839-842.
[7] (Yan Boyang, Wu Chen. Chinese Medical Named Entity Recognition Based on Self-Attention[J]. Computer & Digital Engineering, 2022, 50(4): 839-842.)
[8] 张厚昌, 刘成良. 融合嵌入字词特征的中文医疗命名实体识别[J]. 中华医学图书情报杂志, 2021, 30(9): 42-49.
[8] (Zhang Houchang, Liu Chengliang. Recognition of Chinese-Named Medical Entities Embedded Words Character[J]. Chinese Journal of Medical Library and Information Science, 2021, 30(9): 42-49.)
[9] 胡吉明, 钱玮, 文鹏, 等. 基于结构功能和实体识别的文本语义表示——以病历领域为例[J]. 数据分析与知识发现, 2022, 6(8): 110-121.
[9] (Hu Jiming, Qian Wei, Wen Peng, et al. Text Semantic Representation with Structure-Function and Entity Recognition: Case Study of Medical Records[J]. Data Analysis and Knowledge Discovery, 2022, 6(8): 110-121.)
[10] 巩敦卫, 张永凯, 郭一楠, 等. 融合多特征嵌入与注意力机制的中文电子病历命名实体识别[J]. 工程科学学报, 2021, 43(9): 1190-1196.
[10] (Gong Dunwei, Zhang Yongkai, Guo Yinan, et al. Named Entity Recognition of Chinese Electronic Medical Records Based on Multifeature Embedding and Attention Mechanism[J]. Chinese Journal of Engineering, 2021, 43(9): 1190-1196.)
[11] Cao S S, Lu W, Zhou J, et al. Cw2vec: Learning Chinese Word Embeddings with Stroke N-Gram Information[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018, 32(1).
[12] Wan Q, Liu J, Wei L N, et al. A Self-Attention Based Neural Architecture for Chinese Medical Named Entity Recognition[J]. Mathematical Biosciences and Engineering: MBE, 2020, 17(4): 3498-3511.
doi: 10.3934/mbe.2020197
[13] 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.
[13] (Luo Ling, Yang Zhihao, Song Yawen, 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.)
[14] 景慎旗, 赵又霖. 面向中文电子病历文书的医学命名实体识别研究——一种基于半监督深度学习的方法[J]. 信息资源管理学报, 2021, 11(6): 105-115.
[14] (Jing Shenqi, Zhao Youlin. Recognizing Clinical Named Entity from Chinese Electronic Medical Record Texts Based on Semi-Supervised Deep Learning[J]. Journal of Information Resources Management, 2021, 11(6): 105-115.)
[15] 屈倩倩, 阚红星. 基于Bert-BiLSTM-CRF的中医文本命名实体识别[J]. 电子设计工程, 2021, 29(19): 40-43.
[15] (Qu Qianqian, Kan Hongxing. Named Entity Recognition of Chinese Medical Text Based on Bert-BiLSTM-CRF[J]. Electronic Design Engineering, 2021, 29(19): 40-43.)
[16] 张云秋, 汪洋, 李博诚. 基于RoBERTa-wwm动态融合模型的中文电子病历命名实体识别[J]. 数据分析与知识发现, 2022, 6(2/3): 242-250.
[16] (Zhang Yunqiu, Wang Yang, Li Bocheng. Identifying Named Entities of Chinese Electronic Medical Records Based on RoBERTa-wwm Dynamic Fusion Model[J]. Data Analysis and Knowledge Discovery, 2022, 6(2/3): 242-250.)
[17] 张芳丛, 秦秋莉, 姜勇, 等. 基于RoBERTa-WWM-BiLSTM-CRF的中文电子病历命名实体识别研究[J]. 数据分析与知识发现, 2022, 6(2/3): 251-262.
[17] (Zhang Fangcong, Qin Qiuli, Jiang Yong, et al. Named Entity Recognition for Chinese EMR with RoBERTa-WWM-BiLSTM-CRF[J]. Data Analysis and Knowledge Discovery, 2022, 6(2/3): 251-262.)
[18] 李梦蝶, 张平, 李功利, 等. 中文医学命名实体识别算法研究[J]. 医学信息学杂志, 2022, 43(3): 45-51.
[18] (Li Mengdie, Zhang Ping, Li Gongli, et al. Study on Chinese Medical Named Entity Recognition Algorithm[J]. Journal of Medical Informatics, 2022, 43(3): 45-51.)
[19] 余俊康. 多任务学习的中文电子病历命名实体识别研究[J]. 软件导刊, 2021, 20(11): 42-46.
[19] (Yu Junkang. Chinese Electronic Medical Record Naming Entity Recognition Based on Multi-Task Learning[J]. Software Guide, 2021, 20(11): 42-46.)
[20] 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[EB/OL]. [2022-08-08]. https://conference.bj.bcebos.com/ccks2019/eval/webpage/pdfs/eval_paper_1_1_1.pdf.
[20] (Qiao Rui, Yang Xiaoran, Huang Wenkang. Medical Named Entity Recognition Based on BERT and Model Fusion[EB/OL]. [2022-08-08]. https://conference.bj.bcebos.com/ccks2019/eval/webpage/pdfs/eval_paper_1_1_1.pdf.)
[21] Liu M, Zhou X, Cao Z, et al. Team MSIIP at CCKS 2019 Task 1[EB/OL]. [2022-08-08]. https://conference.bj.bcebos.com/ccks2019/eval/webpage/pdfs/eval_paper_1_1_2.pdf.
[22] Li N, Luo L, Ding Z, et al. DUTIR at the CCKS-2019 Task1: Improving Chinese Clinical Named Entity Recognition Using Stroke ELMo and Transfer Learning[C]// Proceedings of the 4th Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing. 2019: 24-27.
[23] Li Z, Gan Z, Zhang B, et al. Noisy Label Learning for Chinese Medical Named Entity Recognition Based on Uncertainty Strategy[EB/OL]. [2022-08-08]. https://bj.bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_eval_paper_3_1_1.pdf.
[24] 晏阳天, 赵新宇, 吴贤. 基于BERT与字形字音特征的医疗命名实体识别[EB/OL]. [2022-08-08]. https://bj.bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_eval_paper_3_1_2.pdf.
[24] (Yan Yangtian, Zhao Xinyu, Wu Xian. Medical Named Entity Recognition Based on BERT and Glyph Phonetic Characteristics[EB/OL]. [2022-08-08]. https://bj.bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_eval_paper_3_1_2.pdf.)
[25] 杨文明, 毕金良, 邹佳丽, 等. 基于ChiEHRBert 与多模型融合的医疗命名实体识别[EB/OL]. [2022-08-08]. https://bj.bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_eval_paper_3_1_3.pdf.
[25] (Yang Wenming, Bi Jinliang, Zou Jiali, et al. Medical Named Entity Recognition Based on ChiEHRBert and Muti-Model Fusion[EB/OL]. [2022-08-08]. https://bj.bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_eval_paper_3_1_3.pdf.)
[26] Qiu J H, Zhou Y M, Wang Q, et al. Chinese Clinical Named Entity Recognition Using Residual Dilated Convolutional Neural Network with Conditional Random Field[J]. IEEE Transactions on Nanobioscience, 2019, 18(3): 306-315.
doi: 10.1109/TNB.7728
[27] Kong J, Zhang L, Jiang M, et al. Incorporating Multi-Level CNN and Attention Mechanism for Chinese Clinical Named Entity Recognition[J]. Journal of Biomedical Informatics, 2021, 116: 103737.
doi: 10.1016/j.jbi.2021.103737
[28] Zhang R Y, Zhao P, Guo W, et al. Medical Named Entity Recognition Based on Dilated Convolutional Neural Network[J]. Cognitive Robotics, 2022, 2: 13-20.
doi: 10.1016/j.cogr.2021.11.002
[29] An Y, Xia X, Chen X, et al. Chinese Clinical Named Entity Recognition via Multi-Head Self-Attention Based BiLSTM-CRF[J]. Artificial Intelligence in Medicine, 2022, 127: 102282.
doi: 10.1016/j.artmed.2022.102282
[30] Tang B Z, Wang X L, Yan J, et al. Entity Recognition in Chinese Clinical Text Using Attention-Based CNN-LSTM-CRF[J]. BMC Medical Informatics and Decision Making, 2019, 19(S3): 74.
doi: 10.1186/s12911-019-0787-y
[31] Ji B, Liu R, Li S S, et al. A Hybrid Approach for Named Entity Recognition in Chinese Electronic Medical Record[J]. BMC Medical Informatics and Decision Making, 2019, 19(S2): 64.
doi: 10.1186/s12911-019-0767-2
[32] Xiong Y, Peng H, Xiang Y, et al. Leveraging Multi-Source Knowledge for Chinese Clinical Named Entity Recognition via Relational Graph Convolutional Network[J]. Journal of Biomedical Informatics, 2022, 128: 104035.
doi: 10.1016/j.jbi.2022.104035
[33] He Q Z, Wu L, Yin Y D, et al. Knowledge-Graph Augmented Word Representations for Named Entity Recognition[C]// Proceedings of the 2020 AAAI Conference on Artificial Intelligence. 2020, 34(5): 7919-7926.
[34] Zhou B H, Cai X R, Zhang Y, et al. An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization[C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021: 6214-6224.
[35] Luo L, Li N, Li S C, et al. DUTIR at the CCKS-2018 Task1: A Neural Network Ensemble Approach for Chinese Clinical Named Entity Recognition[C]// Proceedings of the 3rd Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing. 2018: 7-12.
[36] Hu J, Shi X, Liu Z, et al. HITSZ_CNER: A Hybrid System for Entity Recognition from Chinese Clinical Text[EB/OL]. [2022-08-08]. https://ceur-ws.org/Vol-1976/paper05.pdf.
[37] Nie B L, Ding R X, Xie P J, et al. Knowledge-Aware Named Entity Recognition with Alleviating Heterogeneity[C]// Proceedings of the 2021 AAAI Conference on Artificial Intelligence. 2021, 35(15): 13595-13603.
[38] Nakayama H. Seqeval: A Python Framework for Sequence Labeling Evaluation[CP/OL]. [2022-09-10]. https://github.com/chakki-works/seqeval.
[39] CCKS2017中文电子病例命名实体识别测评任务训练数据集[DS/OL]. [2022-09-10].https://github.com/liuhuanyong/MedicalNamedEntityRecognition/blob/master/data/train.txt.
[39] (CCKS2017-Medical Named Entity Recognition Task[DS/OL]. [2022-09-10]. https://github.com/liuhuanyong/MedicalNamedEntityRecognition/blob/master/data/train.txt.)
[40] Yidu-S4KDS/OL. [2022-09-10]. http://openkg1.oss-cn-beijing.aliyuncs.com/590d97bd-18fb-49d1-89f8-d6a3802b2040/yidu-s4k.zip.
[41] IMCS21DS/OL.[2022-09-10]. https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414.
[42] Yin Z, Shen Y Y. On the Dimensionality of Word Embedding[OL]. arXiv Preprint, arXiv: 1812.04224.
[43] Cui Y M, Che W X, Liu T, et al. Pre-Training with Whole Word Masking for Chinese BERT[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 3504-3514.
doi: 10.1109/TASLP.2021.3124365
[44] Cui Y M, Che W X, Liu T, et al. Revisiting Pre-Trained Models for Chinese Natural Language Processing[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020.
[1] 赵蕊洁, 佟昕瑀, 刘小桦, 路永和. 基于神经网络的医药科技论文实体识别与标注研究*[J]. 数据分析与知识发现, 2022, 6(9): 100-112.
[2] 成全, 佘德昕. 融合患者体征与用药数据的图神经网络药物推荐方法研究*[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[3] 唐娇, 张力生, 桑春艳. 基于潜在主题分布和长、短期用户表示的新闻推荐模型*[J]. 数据分析与知识发现, 2022, 6(9): 52-64.
[4] 游新冬, 袁梦龙, 张乐, 吕学强. CNN-SM:基于义原与多特征融合的消费品领域缺陷词识别模型*[J]. 数据分析与知识发现, 2022, 6(9): 77-85.
[5] 杨美芳, 杨波. 基于笔画ELMo嵌入IDCNN-CRF模型的企业风险领域实体抽取研究*[J]. 数据分析与知识发现, 2022, 6(9): 86-99.
[6] 胡吉明, 钱玮, 文鹏, 吕晓光. 基于结构功能和实体识别的文本语义表示——以病历领域为例*[J]. 数据分析与知识发现, 2022, 6(8): 110-121.
[7] 赵鹏武, 李志义, 林小琦. 基于注意力机制和卷积神经网络的中文人物关系抽取与识别*[J]. 数据分析与知识发现, 2022, 6(8): 41-51.
[8] 周宁, 靳高雅, 石雯茜. 融合神经网络与全局推理的实体共指消解算法*[J]. 数据分析与知识发现, 2022, 6(8): 75-83.
[9] 杨文丽, 李娜娜. 基于对抗网络的文本对齐跨语言情感分类方法*[J]. 数据分析与知识发现, 2022, 6(7): 141-151.
[10] 张若琦, 申建芳, 陈平华. 结合GNN、Bi-GRU及注意力机制的会话序列推荐*[J]. 数据分析与知识发现, 2022, 6(6): 46-54.
[11] 郭樊容, 黄孝喜, 王荣波, 谌志群, 胡创, 谢一敏, 司博宇. 基于Transformer和图卷积神经网络的隐喻识别*[J]. 数据分析与知识发现, 2022, 6(4): 120-129.
[12] 张云秋, 汪洋, 李博诚. 基于RoBERTa-wwm动态融合模型的中文电子病历命名实体识别*[J]. 数据分析与知识发现, 2022, 6(2/3): 242-250.
[13] 余传明, 林虹君, 张贞港. 基于多任务深度学习的实体和事件联合抽取模型*[J]. 数据分析与知识发现, 2022, 6(2/3): 117-128.
[14] 张芳丛, 秦秋莉, 姜勇, 庄润涛. 基于RoBERTa-WWM-BiLSTM-CRF的中文电子病历命名实体识别研究[J]. 数据分析与知识发现, 2022, 6(2/3): 251-262.
[15] 韦婷婷, 江涛, 郑舒玲, 张建桃. 融合LSTM与逻辑回归的中文专利关键词抽取*[J]. 数据分析与知识发现, 2022, 6(2/3): 308-317.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn