Drug Specification Named Entity Recognition base on BiLSTM-CRF Model

被引：9

作者：

Li, Wei-Yan ^{[1
]}

Song, Wen-Ai ^{[1
]}

Jia, Xin-Hong ^{[1
]}

Yang, Ji-Jiang ^{[2
]}

Wang, Qing ^{[2
]}

Lei, Yi ^{[3
]}

Huang, Ke ^{[4
,5
,6
]}

Li, Jun ^{[4
,5
,6
]}

Yang, Ting ^{[4
,5
,6
]}

机构：

[1] North Univ China, Software Sch, Taiyuan, Shanxi, Peoples R China

[2] Tsinghua Univ, Res Inst Informat Technol, Beijing, Peoples R China

[3] Beijing Dfus Co Ltd, Beijing, Peoples R China

[4] China Japan Friendship Hosp, Dept Pulm & Crit Care Med, Beijing, Peoples R China

[5] Natl Clin Res Ctr Resp Dis, Beijing, Peoples R China

[6] Chinese Acad Med Sci, Inst Resp Med, Beijing, Peoples R China

来源：

2019 IEEE 43RD ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 2 | 2019年

关键词：

BiLSTM; CRF; Named Entity Recognition; Deep Learning; Drug Specification;

D O I：

10.1109/COMPSAC.2019.10244

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In order to realize automatic recognition and extraction of entities in unstructured medical texts, a model combining language model conditional random field algorithm (CRF) and Bi-directional Long Short-term Memory networks (BiLSTM) is proposed. We crawled 804 drug specifications for treating asthma from the Internet, and then quantized the normalized field of drug specification word by a vector as the input of the neural network. Compared with the traditional machine learning algorithm CRF model, the system accuracy, recall and F1 value are improved by 6.18%, 5.2% and 4.87%. This model is applicable to extract named entity information from drug specification.

引用

页码：429 / 433

页数：5

共 50 条

[21] Named Entity Recognition by Using XLNet-BiLSTM-CRF
Yan, Rongen
Jiang, Xue
Dang, Depeng
[J]. NEURAL PROCESSING LETTERS, 2021, 53 (05) : 3339 - 3356
[22] Document-level attention-based BiLSTM-CRF incorporating disease dictionary for disease named entity recognition
Xu, Kai
Yang, Zhenguo
Kang, Peipei
Wang, Qi
Liu, Wenyin
[J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2019, 108 : 122 - 132
[23] Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF
An, Ying
Xia, Xianyun
Chen, Xianlai
Wu, Fang-Xiang
Wang, Jianxin
[J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2022, 127
[24] HAZOP Text Named Entity Recognition using CNN-BilSTM-CRF Model
Gao, Dong
Peng, Lanfei
Bai, Yujie
[J]. 2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 6159 - 6164
[25] A HYBRID CNN-BILSTM MODEL FOR DRUG NAMED ENTITY RECOGNITION
Fudholi, Dhomas Hatta
Nayoan, Royan Abida N.
Hidayatullah, Ahmad Fathan
Arianto, Dede Brahma
[J]. JOURNAL OF ENGINEERING SCIENCE AND TECHNOLOGY, 2022, 17 (01): : 730 - 744
[26] Research on entity recognition and alignment of APT attack based on Bert and BiLSTM-CRF
Yang, Xiuzhang
Peng, Guojun
Li, Zichuan
Lyu, Yangqi
Liu, Side
Li, Chenguang
[J]. Tongxin Xuebao/Journal on Communications, 2022, 43 (06): : 58 - 70
[27] Named entity recognition for Chinese judgment documents based on BiLSTM and CRF
Wenming Huang
Dengrui Hu
Zhenrong Deng
Jianyun Nie
[J]. EURASIP Journal on Image and Video Processing, 2020
[28] Chinese Named Entity Recognition Based on CNN-BiLSTM-CRF
Jia, Yaozong
Xu, Xiaobin
[J]. PROCEEDINGS OF 2018 IEEE 9TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS), 2018, : 831 - 834
[29] Named entity recognition for Chinese judgment documents based on BiLSTM and CRF
Huang, Wenming
Hu, Dengrui
Deng, Zhenrong
Nie, Jianyun
[J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2020, 2020 (01)
[30] A Residual BiLSTM Model for Named Entity Recognition
Yang, Gang
Xu, Hongzhe
[J]. IEEE ACCESS, 2020, 8 : 227710 - 227718

← 1 2 3 4 5 →