Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (2): 90-97    DOI: 10.11925/infotech.2096-3467.2018.0617
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于Bi-LSTM和CRF的药品不良反应抽取模型构建*
朱笑笑,杨尊琦,刘婧()
天津财经大学管理信息系统系 天津 300222
Construction of an Adverse Drug Reaction Extraction Model Based on Bi-LSTM and CRF
Xiaoxiao Zhu,Zunqi Yang,Jing Liu()
Department of Management Information System, Tianjin University of Finance and Economics,Tianjin 300222, China
全文: PDF(608 KB)   HTML ( 10
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】提出处理社会媒体上不规范文本的方法, 以提高社会媒体中药品不良反应抽取效果。【方法】基于TensorFlow深度学习框架, 将LSTM和CRF结合, 借助LSTM能利用上下文信息的特性, 通过CRF层考虑输出标记的依赖关系, 构建基于Bi-LSTM和CRF的药品不良反应抽取模型。【结果】在Twitter数据集上开展系列实验, 结果表明与传统CRF、前向LSTM、后向LSTM和Bi-LSTM相比, Bi-LSTM-CRF可以取得最高的F-measure值(0.7963)。【局限】实验数据源相对单一, 未来可以在多个数据源上验证Bi-LSTM-CRF方法的有效性。【结论】结合LSTM和CRF能够有效处理社会媒体上不规范文本, 所构建的模型可较好识别不良反应实体, 辅助相关部门进行决策。

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
朱笑笑
杨尊琦
刘婧
关键词 社会媒体药品不良反应CRFLSTM    
Abstract

[Objective] To improve the performance of extracting adverse drug reactions from social media, a method is proposed to deal with non-standard texts in social media. [Methods] This method Bi-LSTM-CRF combined LSTM and CRF, and was implemented using TensorFlow. LSTM Could utilize context information, while CRF Could consider the dependence of output tags. An adverse drug reaction extraction model was constructed based on Bi-LSTM-CRF. [Results] A series of experiments were carried out on the Twitter dataset. The experimental results showed that the proposed Bi-LSTM-CRF method achieved the highest F-measure (0.7963) for adverse drug reaction extraction, compared with other methods, including CRF, forward LSTM, backward LSTM, and Bi-LSTM. [Limitations] The experiments were performed on only one corpus, and the validity of the proposed method need be verified on other data sources. [Conclusions] Combining Bi-LSTM and CRF can effectively deal with non-standard texts in social media. The constructed model in this paper can identify adverse drug reactions effectively and support relevant departments in decision-making.

Key wordsSocial Media    Adverse Drug Reactions    CRF    LSTM
收稿日期: 2018-06-04     
基金资助:*本文系国家自然科学基金青年基金项目“基于文本挖掘的社会媒体药品不良反应抽取研究”(项目编号: 71701142)和天津财经大学本科生科研训练计划“基于互联网数据的“药品百事通”决策支持系统研究”(项目编号: SRT201799)的研究成果之一
引用本文:   
朱笑笑,杨尊琦,刘婧. 基于Bi-LSTM和CRF的药品不良反应抽取模型构建*[J]. 数据分析与知识发现, 2019, 3(2): 90-97.
Xiaoxiao Zhu,Zunqi Yang,Jing Liu. Construction of an Adverse Drug Reaction Extraction Model Based on Bi-LSTM and CRF. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2018.0617.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2018.0617
[1] Hammond M.Users of the World, Unite! The Challenges and Opportunities of Social Media[J]. Business Horizons, 2010, 53(1): 59-68.
[2] Andreu P J, Poon C, Merrifield R, et al.Big Data for Health[J]. IEEE Journal of Biomedical & Health Informatics, 2015, 19(4): 1.
[3] Roughead E E, Semple S J.Medication Safety in Acute Care in Australia: Where are We Now? Part 1: A Review of the Extent and Causes of Medication Problems 2002-2008[J]. Australia & New Zealand Health Policy, 2009, 6(1): 1-12.
[4] Liu J, Zhao S, Zhang X.An Ensemble Method for Extracting Adverse Drug Events from Social Media[J]. Artificial Intelligence in Medicine, 2016, 70(9): 62-76.
[5] Yang C C, Yang H, Jiang L, et al.Social Media Mining for Drug Safety Signal Detection[C]// Proceedings of the 2012 International Workshop on Smart Health and Wellbeing. 2012.
[6] Ioannis K, Azadeh N, Matthew S, et al.Analysis of the Effect of Sentiment Analysis on Extracting Adverse Drug Reactions from Tweets and Forum Posts[J]. Journal of Biomedical Informatics, 2016, 62: 148-158.
[7] Azadeh N, Abeed S, Karen O, et al.Pharmacovigilance from Social Media: Mining Adverse Drug Reaction Mentions Using Sequence Labeling with Word Embedding Cluster Features[J]. Journal of the American Medical Informatics Association Jamia, 2015, 22(3): 671-681.
[8] Hochreiter S, Schmidhuber J.Long Short-Term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[9] Lafferty J D, McCallum A, Pereira F C N. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data[C]//Proceedings of the 18th International Conference on Machine Learning. 2001.
[10] Jiang K, Zheng Y.Mining Twitter Data for Potential Drug Effects[A]// Advanced Data Mining and Applications[M]. Berlin, Heidelberg: Springer, 2013: 434-443.
[11] Leaman R, Wojtulewicz L, Sullivan R, et al.Towards Internet-Age Pharmacovigilance: Extracting Adverse Drug Reactions from User Posts to Health-Related Social Networks[C]// Proceedings of the 2010 Workshop on Biomedical Natural Language Processing. 2010: 117-125.
[12] Liu X, Chen H.A Research Framework for Pharmacovigilance in Health Social Media: Identification and Evaluation of Patient Adverse Drug Event Reports[J]. Journal of Biomedical Informatics, 2015, 58: 268-279.
[13] Bian J, Topaloglu U, Yu F.Towards Large-scale Twitter Mining for Drug-related Adverse Events[C]// Proceedings of the 2012 International Workshop on Smart Health and Wellbeing. 2012.
[14] Benton A, Ungar L, Hill S, et al.Identifying Potential Adverse Effects Using the Web: A New Approach to Medical Hypothesis Generation[J]. Journal of Biomedical Informatics, 2011, 44(6): 989-989.
[15] Wu D J H, Man C F, Kwong K, et al. Postmarketing Drug Safety Surveillance[J]. Pharmaceutical Development & Regulation, 2003, 1(4): 231-244.
[16] Freifeld C C, Brownstein J S, Menone C M, et al.Digital Drug Safety Surveillance: Monitoring Pharmaceutical Products in Twitter[J]. Drug Safety, 2014, 37(5): 343-344.
[17] Sampathkumar H, Chen X W, Luo B.Mining Adverse Drug Reactions from Online Healthcare Forums Using Hidden Markov Model[J]. BMC Medical Informatics & Decision Making, 2014, 14(1): 91-92.
[18] Rastegarmojarad M, Liu H, Nambisan P.Using Social Media Data to Identify Potential Candidates for Drug Repurposing: A Feasibility Study[J]. JMIR Research Protocols, 2016, 5(2): e121.
[19] Feldman R, Netzer O, Peretz A, et al.Utilizing Text Mining on Online Medical Forums to Predict Label Change due to Adverse Drug Reactions[C]// Proceedings of the 2015 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015: 1779-1788.
[20] Metkejimenez A, Karimi S. Concept Extraction to Identify Adverse Drug Reactions in Medical Forums: A Comparison of Algorithms[OL]. arXiv Preprint, arXiv:1504.06936v1.
[21] Lai S, Liu K, He S, et al.How to Generate a Good Word Embedding[J]. IEEE Intelligent Systems, 2016, 31(6): 5-14.
[22] Dyer C, Ballesteros M, Ling W, et al. Transition-Based Dependency Parsing with Stack Long Short-Term Memory[OL]. arXiv Preprint, arXiv:1505.08075v1.
[23] Chen X, Qiu X, Zhu C, et al.Long Short-Term Memory Neural Networks for Chinese Word Segmentation[C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 1197-1206.
[24] Viterbi A.Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm[J]. IEEE Transactions on Informatation Theory, 1967, 13(2): 260-269.
[25] Friggstad Z, Rezapour M, Salavatipour M R.Local Search Yields a PTAS for k-Means in Doubling Metrics[A]// Foundations of Computer Science[M]. IEEE, 2016: 365-374.
[26] Davidian D. Feed-forward Neural Network: USA, US5438646[P].1995-08-01.
[27] Rumelhart D E, Hinton G E, Williams R J.Learning Representations by Back-propagating Errors[J]. Nature, 1986, 323(6088): 399-421.
[28] Graves A, Schmidhuber J.Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures[J]. Neural Network, 2005, 18(5): 602-610.
[29] Lin B Y, Xu F, Luo Z, et al.Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media[C]//Proceedings of the 3rd Workshop on Noisy User-generated Text. 2017: 160-165.
[30] Palangi H, Deng L, Shen Y, et al.Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval[J]. IEEE/ACM Transactions on Audio Speech & Language Processing, 2016, 24(4): 694-707.
[31] Soltau H, Liao H, Sak H. Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition[OL]. arXiv Preprint, arXiv:1610.09975v1.
[32] Carlezon W A, Béguin C, Knoll A T, et al.Kappa-Opioid Ligands in the Study and Treatment of Mood Disorders[J]. Pharmacology & Therapeutics, 2009, 123(3): 334-343.
[33] Yang E S, Kim J D, Park C Y, et al.Hyperparameter Tuning for Hidden Unit Conditional Random Fields[J]. Engineering Computations, 2017, 34(6): 2054-2062.
[34] Xu W, Auli M, Clark S.Expected F-Measure Training for Shift-Reduce Parsing with Recurrent Neural Networks[C]// Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016: 210-220.
[1] 余丽,钱力,付常雷,赵华茗. 基于深度学习的文本中细粒度知识元抽取方法研究*[J]. 数据分析与知识发现, 2019, 3(1): 38-45.
[2] 冯国明,张晓冬,刘素辉. 基于自主学习的专业领域文本DBLC分词模型[J]. 数据分析与知识发现, 2018, 2(5): 40-47.
[3] 齐惠颖,郭建光. 基于CDISC标准的多源临床研究数据整合关键技术与实现*[J]. 数据分析与知识发现, 2018, 2(5): 88-93.
[4] 邓三鸿,傅余洋子,王昊. 基于LSTM模型的中文图书多标签分类研究*[J]. 数据分析与知识发现, 2017, 1(7): 52-60.
[5] 王晓玉,李斌. 基于CRFs和词典信息的中古汉语自动分词*[J]. 数据分析与知识发现, 2017, 1(5): 62-70.
[6] 谭旻, 许鑫, 赵星. 学术博客共推荐关系及核心结构特性研究——以科学网博客为例[J]. 现代图书情报技术, 2015, 31(7-8): 24-30.
[7] 孟美任, 丁晟春. 在线中文商品评论可信度研究[J]. 现代图书情报技术, 2013, 29(9): 60-66.
[8] 王昊,邓三鸿. HMM和CRFs在信息抽取应用中的比较研究[J]. 现代图书情报技术, 2007, 2(12): 57-63.
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