High-precision entity and relation extraction in medical domain based on pseudo-entity data augmentation

doi:10.11772/j.issn.1001-9081.2023020143

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (2): 393-402.DOI: 10.11772/j.issn.1001-9081.2023020143

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

High-precision entity and relation extraction in medical domain based on pseudo-entity data augmentation

Andi GUO¹, Zhen JIA¹, Tianrui LI¹^,²()

^1.School of Computing and Artificial Intelligence，Southwest Jiaotong University，Chengdu Sichuan 611756，China
^2.National Engineering Laboratory of Integrated Transportation Big Data Application Technology （Southwest Jiaotong University），Chengdu Sichuan 611756，China

Received:2023-02-20 Revised:2023-03-21 Accepted:2023-04-03 Online:2023-08-14 Published:2024-02-10
Contact: Tianrui LI
About author:GUO Andi， born in 1998， M. S. candidate. His research interests include natural language processing， knowledge graph.
JIA Zhen， born in 1975， Ph. D.， lecturer. Her research interests include intelligent question answering， knowledge graph.
Supported by:
National Natural Science Foundation of China(62276218)

基于伪实体数据增强的高精准率医学领域实体关系抽取

郭安迪¹, 贾真¹, 李天瑞¹^,²()

^1.西南交通大学计算机与人工智能学院，成都 611756
^2.综合交通大数据应用技术国家工程实验室（西南交通大学），成都 611756

通讯作者: 李天瑞
作者简介:郭安迪（1998—），男，山东菏泽人，硕士研究生，CCF学生会员，主要研究方向：自然语言处理、知识图谱
贾真（1975—），女，河北保定人，讲师，博士，CCF会员，主要研究方向：智能问答、知识图谱；
基金资助:
国家自然科学基金资助项目(62276218)

Abstract

Abstract:

Aiming at the problems of dense knowledge and the propagation of error during entity extraction and relation classification in medical domain， a high-precision entity and relation extraction framework based on pseudo-entity data augmentation was proposed. First， a Transformer-based feature reading unit was added in the entity extraction module to capture category information for accurately identifying medical long entities among dense entities. Second， a relation negative example generation module was inserted into the pipeline extraction framework， pseudo-entities were generated for confusing relation classification model by an under-sampling-based pseudo-entity generation model， and three data augmentation generation strategies were proposed to improve the model’s ability to identify subject-object reversal， subject-object boundary errors， and relation classification errors. Finally， the problem of the sharp increase in training time caused by data enhancement was alleviated by the levitated-marker-based relation classification model. On CMeIE dataset， four mainstream models were compared with the proposed model. For entity extraction tasks， the proposed model improved the F1 value by 2.26% compared with suboptimal model PL-Marker（Packed Levitated Marker）， while for entity relation extraction tasks， the proposed medel improved the F1 value by 5.45% and the precision by 15.62% compared with suboptimal pipeline extraction model proposed by CBLUE （Chinese Biomedical Language Understanding Evaluation）. The experimental results show that using both the feature reading unit and the pseudo-entity data enhancement module can effectively improve the precision of extraction.

Key words: entity and relation extraction, data augmentation, high-precision, medical domain, relation negative example generation

摘要：

针对医学领域知识密集、实体抽取和关系分类存在误差传递的问题，提出一种基于伪实体数据增强的高精准率的实体关系抽取框架。首先，在实体抽取模块添加基于Transformer的特征读取单元捕捉类别信息，以在密集的实体中准确识别医学长实体；其次，在流水线抽取框架的基础上插入关系负例生成模块，通过基于欠采样的伪实体生成模型生成混淆关系分类模型的伪实体，并通过三种数据增强生成策略提升模型鉴别主语宾语颠倒、主语宾语边界错误和关系分类错误的能力；最后，通过基于悬浮标记的关系分类模型缓解数据增强带来的训练时间剧增的问题。在CMeIE数据集中，对比了目前主流的4个模型。实体抽取部分相较于次优模型PL-Marker（Packed Levitated Marker），F1值提升了2.26%；实体关系抽取相较于次优模型CBLUE（Chinese Biomedical Language Understanding Evaluation）提出的流水线抽取模型，F1值提升了5.45%，精准率提升了15.62%。实验结果表明使用特征读取单元和伪实体数据增强模块可有效提高抽取的精准率。

关键词: 实体关系抽取, 数据增强, 高精准率, 医学领域, 关系负例生成

CLC Number:

TP391.1

Andi GUO, Zhen JIA, Tianrui LI. High-precision entity and relation extraction in medical domain based on pseudo-entity data augmentation[J]. Journal of Computer Applications, 2024, 44(2): 393-402.

郭安迪, 贾真, 李天瑞. 基于伪实体数据增强的高精准率医学领域实体关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 393-402.

Figures/Tables 14

Fig. 1 Schematic diagram of overall model process

Fig. 2 Schematic diagram of TFRM

Fig. 3 Schematic diagram of USPGM

Tab. 1 Information of CMeIE dataset used in experiment

数据集类型	数据条目	关系数	主语数	宾语数
训练集	14 339	43 660	18 797	41 478
测试集	3 585	10 626	4 627	10 123
增强集	14 339	450 053	26 028	113 630

Fig. 4 Attention mask matrix in LMM

Fig. 5 Distribution of entity segment size

Tab. 2 Details of experimental parameters

模型	预热率	批大小	lr/10^-5	实体抽取		关系分类
模型	预热率	批大小	lr/10^-5	Epoch	最大片段长度	Epoch
SpERT	0.1	2	5	—	20	20
PURE	0.1	32	5	7	—	10
PL-Marker	0.1	32	5	7	20	8
CBLUE	0.1	32	5	7	—	8
本文模型	0.1	32	5	7	—	8

Tab. 3 Comparison of experimental results among different models

模型	实体抽取			关系抽取
模型	P	R	F1	P	R	F1
SpERT	59.66	78.23	67.70	46.79	46.86	46.82
PURE	72.94	70.48	71.69	53.87	48.70	51.16
PL-Marker	75.47	70.55	72.92	57.71	50.08	53.63
CBLUE	72.76	72.10	72.43	59.65	49.23	53.94
本文模型	76.01	73.20	74.57	68.97	48.39	56.88

Fig. 6 Sampling number-model performance line chart

Tab. 4 Comparison of experimental results of entity extraction models

模型	关系抽取
模型	P	R	F1
Ground Truth	85.69	60.08	70.64
PURE	67.84	44.48	53.73
PL-Marker	69.52	45.29	54.85
CBLUE	69.08	47.47	56.27
TFRM	69.97	48.39	56.88

Tab. 5 Comparison experiment results of TFRU module parameters

模型	实体抽取			实体关系抽取
模型	P	R	F1	P	R	F1
未用TFRU	71.52	72.04	71.52	69.08	47.47	56.27
1层 TFRU	76.80	71.94	74.29	70.22	46.46	55.92
2层 TFRU	76.01	73.20	74.57	69.97	48.39	56.88
3层 TFRU	76.47	72.96	74.67	69.98	48.14	56.86

Fig. 7 TFRU attention visualization

Tab. 6 Ablation experimental results of automatic generation module of relation negative examples

增强策略	实标记				悬浮标记
增强策略	P/%	R/%	F1/%	每秒采样数	P/%	R/%	F1/%	每秒采样数
$T g t$	59.65	49.23	53.94	173.7	57.71	50.08	53.63	729.8
$T g t + T g t_r e v e r s e$	57.71	52.01	54.71		58.86	51.86	54.90
$T g t + T g t_r e v e r s e_l a b e l$	57.61	52.08	54.71		57.60	52.00	54.65
$T g t + T p s e u d o$	60.43	51.99	55.89		60.48	51.22	55.47
$T g t + T g t_r e v e r s e + T p s e u d o$	61.97	51.13	56.03		61.94	50.69	55.75
$T g t + T g t_r e v e r s e_l a b e l + T p s e u d o$	62.15	50.75	55.87		62.17	50.91	55.98
$T g t + T U S P G M_p s e u d o$	68.09	47.00	55.61		67.68	47.42	55.77
$T g t + T g t_r e v e r s e + T U S P G M_p s e u d o$	67.85	44.97	54.09		68.97	48.39	56.88
$T g t + T g t_r e v e r s e_l a b e l + T U S P G M_p s e u d o$	72.48	45.06	55.57		71.12	46.46	56.20

Tab. 6 Ablation experimental results of automatic generation module of relation negative examples

增强策略	实标记				悬浮标记
增强策略	P/%	R/%	F1/%	每秒采样数	P/%	R/%	F1/%	每秒采样数
$T g t$	59.65	49.23	53.94	173.7	57.71	50.08	53.63	729.8
$T g t + T g t_r e v e r s e$	57.71	52.01	54.71		58.86	51.86	54.90
$T g t + T g t_r e v e r s e_l a b e l$	57.61	52.08	54.71		57.60	52.00	54.65
$T g t + T p s e u d o$	60.43	51.99	55.89		60.48	51.22	55.47
$T g t + T g t_r e v e r s e + T p s e u d o$	61.97	51.13	56.03		61.94	50.69	55.75
$T g t + T g t_r e v e r s e_l a b e l + T p s e u d o$	62.15	50.75	55.87		62.17	50.91	55.98
$T g t + T U S P G M_p s e u d o$	68.09	47.00	55.61		67.68	47.42	55.77
$T g t + T g t_r e v e r s e + T U S P G M_p s e u d o$	67.85	44.97	54.09		68.97	48.39	56.88
$T g t + T g t_r e v e r s e_l a b e l + T U S P G M_p s e u d o$	72.48	45.06	55.57		71.12	46.46	56.20

Tab. 7 Case analysis

案例	类别	实体关系样例
案例一	标准答案	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为吉兰-巴雷综合征的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0 宾语$ 和［共济失调］ $临床表现 1 宾语$ ，无肢体瘫痪
	未进行数据增强	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为［吉兰-巴雷综合征］ $临床表现 2, 临床表现 3 主语$ 的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0, 临床表现 2 宾语$ 和［共济失调］ $临床表现 1, 临床表现 3 宾语$ ，无肢体瘫痪
	数据增强	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为吉兰-巴雷综合征的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0 宾语$ 和［共济失调］ $临床表现 1 宾语$ ，无肢体瘫痪
案例二	标准答案	［室上速］ $鉴别诊断主语$ 与 $[室性心动过速] 鉴别诊断宾语$ $同义词主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为地高辛可促使室速的患儿发生室性颤动
	未进行数据增强	［室上速］ $同义词 0, 药物治疗 0 主语$ 与 $[室性心动过速] 同义词 0 宾语$ $同义词 1, 药物治疗 1 主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为［地高辛］ $药物治疗 1 宾语$ 可促使室速的患儿发生室性颤动
	数据增强	［室上速］ $鉴别诊断主语$ 与 $[室性心动过速] 鉴别诊断宾语$ $同义词主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为地高辛可促使室速的患儿发生室性颤动。

Tab. 7 Case analysis

案例	类别	实体关系样例
案例一	标准答案	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为吉兰-巴雷综合征的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0 宾语$ 和［共济失调］ $临床表现 1 宾语$ ，无肢体瘫痪
	未进行数据增强	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为［吉兰-巴雷综合征］ $临床表现 2, 临床表现 3 主语$ 的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0, 临床表现 2 宾语$ 和［共济失调］ $临床表现 1, 临床表现 3 宾语$ ，无肢体瘫痪
	数据增强	［Miller-Fisher综合征］ $主语临床表现 0, 临床表现 1, 同义词$ $[M F S] 同义词宾语$ 为吉兰-巴雷综合征的特殊亚型。临床主要表现为［眼部肌肉麻痹］ $临床表现 0 宾语$ 和［共济失调］ $临床表现 1 宾语$ ，无肢体瘫痪
案例二	标准答案	［室上速］ $鉴别诊断主语$ 与 $[室性心动过速] 鉴别诊断宾语$ $同义词主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为地高辛可促使室速的患儿发生室性颤动
	未进行数据增强	［室上速］ $同义词 0, 药物治疗 0 主语$ 与 $[室性心动过速] 同义词 0 宾语$ $同义词 1, 药物治疗 1 主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为［地高辛］ $药物治疗 1 宾语$ 可促使室速的患儿发生室性颤动
	数据增强	［室上速］ $鉴别诊断主语$ 与 $[室性心动过速] 鉴别诊断宾语$ $同义词主语$ $以下简称 [室速] 同义词宾语$ 的鉴别十分重要，因为地高辛可促使室速的患儿发生室性颤动。

References 31

1	宁尚明，滕飞，李天瑞.基于多通道自注意力机制的电子病历实体关系抽取［J］.计算机学报，2020，43（5）： 916-929. 10.11897/SP.J.1016.2020.00916
	NING S M， TENG F， LI T R. Multi-channel self-attention mechanism for relation extraction in clinical records ［J］. Chinese Journal of Computers， 2020， 43（5）： 916-929. 10.11897/SP.J.1016.2020.00916
2	ZHONG Z， CHEN D. A frustratingly easy approach for entity and relation extraction ［C］// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsberg： ACL， 2021： 50-61. 10.18653/v1/2021.naacl-main.5
3	YE D， LIN Y， LI P， et al. Packed levitated marker for entity and relation extraction ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsberg： ACL， 2022： 4904-4917. 10.18653/v1/2022.acl-long.337
4	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
5	BLASCHKE C， VALENCIA A. The frame-based module of the SUISEKI information extraction system ［J］. IEEE Intelligent Systems， 2002， 17（2）： 14-20. 10.1109/mis.2002.999215
6	CORNEY D P， JONES D T， BUXTON B F， et al. Extracting biological information from full-length papers：RN/ 03/17 ［R/OL］.［2022-02-01］. . 10.1093/bioinformatics/bth386
7	FUNDEL K， KÜFFNER R， ZIMMER R. RelEx — Relation extraction using dependency parse trees ［J］. Bioinformatics， 2007， 23（3）： 365-371. 10.1093/bioinformatics/btl616
8	ZHAO Z， YANG Z， SUN C， et al. A hybrid protein-protein interaction triple extraction method for biomedical literature ［C］// Proceedings of the 2017 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway： IEEE， 2017： 1515-1521. 10.1109/bibm.2017.8217886
9	KORDJAMSHIDI P， ROTH D， M-F MOENS. Structured learning for spatial information extraction from biomedical text： bacteria biotopes ［J］. BMC Bbioinformatics， 2015， 16： Article No. 129. 10.1186/s12859-015-0542-z
10	KORDJAMSHIDI P， VAN OTTERLO M， M-F MOENS. Spatial role labeling： towards extraction of spatial relations from natural language ［J］. ACM Transactions on Speech and Language Processing， 2011， 8（3）： Article No. 4. 10.1145/2050104.2050105
11	刘奔，姬东鸿.药物实体和药物相互关系的联合识别［J］.计算机工程与设计，2017，38（5）：1377-1381. 10.16208/j.issn1000-7024.2017.05.048
	LIU B， JI D H. Joint extraction of drug entity and drug-drug interaction［J］. Computer Engineering and Design， 2017， 38（5）： 1377-1381. 10.16208/j.issn1000-7024.2017.05.048
12	LI F， ZHANG M， FU G， et al. A neural joint model for entity and relation extraction from biomedical text ［J］. BMC Bioinformatics， 2017， 18： Article No. 198. 10.1186/s12859-017-1609-9
13	BEKOULIS G， DELEU J， DEMEESTER T， et al. Adversarial training for multi-context joint entity and relation extraction ［EB/OL］. （2019-01-14）［2022-05-06］. . 10.18653/v1/d18-1307
14	张世豪，杜圣东，贾真，等.基于深度神经网络和自注意力机制的医学实体关系抽取［J］.计算机科学，2021，48（10）： 77-84. 10.11896/jsjkx.210300271
	ZHANG S H， DU S D， JIA Z， et al. Medical entity relation extraction based on deep neural network and self-attention mechanism ［J］. Computer Science， 2021， 48（10）： 77-84. 10.11896/jsjkx.210300271
15	DEVLIN J， CHANG M-W， LEE K， et al. BERT： pre-training of deep bidirectional transformers for language understanding ［EB/OL］. （2019-05-24）［2019-09-01］. . 10.18653/v1/n18-2
16	PETERS M E， NEUMANN M， IYYER M， et al. Deep contextualized word representations［C］// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies （Volume 1： Long Papers）. Stroudsberg： ACL， 2018： 2227-2237. 10.18653/v1/n18-1202
17	LUO L， YANG Z， CAO M， et al. A neural network-based joint learning approach for biomedical entity and relation extraction from biomedical literature ［J］. Journal of Biomedical Informatics， 2020， 103： 103384. 10.1016/j.jbi.2020.103384
18	ZHAO T， YAN Z， CAO Y， et al. Asking effective and diverse questions： a machine reading comprehension based framework for joint entity-relation extraction ［C］// Proceedings of the 29th International Joint Conferences on Artificial Intelligence. California： ijcai.org， 2021： 3948-3954. 10.24963/ijcai.2020/546
19	EBERTS M， ULGES A. Span-based joint entity and relation extraction with transformer pre-training［EB/OL］. ［2023-02-01］. . 10.18653/v1/2021.eacl-main.319
20	SHEN Y， MA X， TANG Y， et al. A trigger-sense memory flow framework for joint entity and relation extraction ［C］// Proceedings of the Web Conference 2021. New York： ACM， 2021： 1704-1715. 10.1145/3442381.3449895
21	FENG S Y， GANGAL V， WEI J， et al. A survey of data augmentation approaches for NLP ［C］// Findings of the Association for Computational Linguistics： ACL-IJCNLP 2021. Stroudsberg： ACL， 2021： 968-988. 10.18653/v1/2021.findings-acl.84
22	WEI J， ZOU K. EDA： Easy data augmentation techniques for boosting performance on text classification tasks ［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsberg： ACL， 2019： 6382-6388. 10.18653/v1/d19-1670
23	ABDOLLAHI M， GAO X， MEI Y， et al. Substituting clinical features using synthetic medical phrases： medical text data augmentation techniques ［J］. Artificial Intelligence in Medicine， 2021， 120（C）： 102167. 10.1016/j.artmed.2021.102167
24	KANG T， PEROTTE A， TANG Y， et al. UMLS-based data augmentation for natural language processing of clinical research literature ［J］. Journal of the American Medical Informatics Association， 2021， 28（4）： 812-823. 10.1093/jamia/ocaa309
25	SENNRICH R， HADDOW B， BIRCH A. Improving neural machine translation models with monolingual data ［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsberg： ACL， 2016： 86-96. 10.18653/v1/p16-1009
26	WANG A， LI L， WU X， et al. Entity relation extraction in the medical domain： based on data augmentation ［J］. Annals of Translational Medicine， 2022， 10（19）： 1061-1073. 10.21037/atm-22-3991
27	KOBAYASHI S. Contextual augmentation： data augmentation by words with paradigmatic relations ［C］// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies （Volume 2： Short Papers）. Stroudsberg： ACL， 2018： 452-457. 10.18653/v1/n18-2072
28	YANG Y， MALAVIYA C， FERNANDEZ J， et al. Generative data augmentation for commonsense reasoning ［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsberg： ACL， 2020： 1008-1025. 10.18653/v1/2020.findings-emnlp.90
29	QUTEINEH H， SAMOTHRAKIS S， SUTCLIFFE R. Textual data augmentation for efficient active learning on tiny datasets ［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsberg： ACL， 2020： 7400-7410. 10.18653/v1/2020.emnlp-main.600
30	WOLF T， DEBUT L， SANH V， et al. HuggingFace’s Transformers： state-of-the-art natural language processing ［EB/OL］.（2020-07-14）［2022-06-03］. . 10.18653/v1/2020.emnlp-demos.6
31	ZHANG N， CHEN M， 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 （Volume 1： Long Papers）. Stroudsberg： ACL， 2022： 7888-7915. 10.18653/v1/2022.acl-long.544

[1]	Dianhui MAO, Xuebo LI, Junling LIU, Denghui ZHANG, Wenjing YAN. Chinese entity and relation extraction model based on parallel heterogeneous graph and sequential attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2018-2025.
[2]	Jiong WANG, Taotao TANG, Caiyan JIA. PAGCL： positive augmentation graph contrastive learning recommendation method without negative sampling [J]. Journal of Computer Applications, 2024, 44(5): 1485-1492.
[3]	Jie GUO, Jiayu LIN, Zuhong LIANG, Xiaobo LUO, Haitao SUN. Recommendation method based on knowledge‑awareness and cross-level contrastive learning [J]. Journal of Computer Applications, 2024, 44(4): 1121-1127.
[4]	Yifei SONG, Yi LIU. Fast adversarial training method based on data augmentation and label noise [J]. Journal of Computer Applications, 2024, 44(12): 3798-3807.
[5]	Xinrong HU, Jingxue CHEN, Zijian HUANG, Bangchao WANG, Xun YAO, Junping LIU, Qiang ZHU, Jie YANG. Graph convolution network-based masked data augmentation [J]. Journal of Computer Applications, 2024, 44(11): 3335-3344.
[6]	Qiujie SUN, Jinggui LIANG, Si LI. Chinese grammatical error correction model based on bidirectional and auto-regressive transformers noiser [J]. Journal of Computer Applications, 2022, 42(3): 860-866.
[7]	Yimin CAO, Lei CAI, Jingyang GAO. Gene data generation method based on generative adversarial network [J]. Journal of Computer Applications, 2022, 42(3): 783-790.
[8]	Yu PENG, Yaolian SONG, Jun YANG. Motor imagery electroencephalography classification based on data augmentation [J]. Journal of Computer Applications, 2022, 42(11): 3625-3632.
[9]	Ping LUO, Ling DING, Xue YANG, Yang XIANG. Chinese event detection based on data augmentation and weakly supervised adversarial training [J]. Journal of Computer Applications, 2022, 42(10): 2990-2995.
[10]	Shuang DENG, Xiaohai HE, Linbo QING, Honggang CHEN, Qizhi TENG. Weakly supervised fine-grained classification method of Alzheimer’s disease based on improved visual geometry group network [J]. Journal of Computer Applications, 2022, 42(1): 302-309.
[11]	LIU Yaxuan, ZHONG Yong. Joint extraction method of entities and relations based on subject attention [J]. Journal of Computer Applications, 2021, 41(9): 2517-2522.
[12]	JIA Chengxun, LAI Hua, YU Zhengtao, WEN Yonghua, YU Zhiqiang. Chinese-Vietnamese pseudo-parallel corpus generation based on monolingual language model [J]. Journal of Computer Applications, 2021, 41(6): 1652-1658.
[13]	LU Xinwei, YU Pengfei, LI Haiyan, LI Hongsong, DING Wenqian. Weakly supervised fine-grained image classification algorithm based on attention-attention bilinear pooling [J]. Journal of Computer Applications, 2021, 41(5): 1319-1325.
[14]	GAN Lan, SHEN Hongfei, WANG Yao, ZHANG Yuejin. Data augmentation method based on improved deep convolutional generative adversarial networks [J]. Journal of Computer Applications, 2021, 41(5): 1305-1313.
[15]	HUO Shoujun, HAO Yan, SHI Huiyu, DONG Yanqing, CAO Rui. Pattern recognition of motor imagery EEG based on deep convolutional network [J]. Journal of Computer Applications, 2021, 41(4): 1042-1048.

High-precision entity and relation extraction in medical domain based on pseudo-entity data augmentation

基于伪实体数据增强的高精准率医学领域实体关系抽取

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 31

Related Articles 15

Recommended Articles

Metrics