药物相互作用是指药物之间存在的抑制或促进等作用。针对目前药物关系抽取模型在长语句中抽取效果较差以及高层特征信息丢失的问题,该文提出了一种结合最短依存路径的胶囊网络关系抽取模型,该方法首先根据原语句解析出两个药物之间的最短依存路径,然后利用双向长短期记忆网络分别获取原语句和最短依存路径的低层语义表示,再将两者结合输入到胶囊网络中,利用胶囊网络的动态路由机制,动态地决定低层胶囊向高层胶囊传送的信息量,避免了高层特征信息丢失的问题,从而提升抽取效果。在DDIExtraction 2013药物相互作用关系抽取任务上的实验结果表明,该文方法的F1值优于目前最优方法1.17%。
Abstract
Drug-Drug interaction refers to the inhibition or promotion between drugs. To improve the current Drug-Drug interaction relationship extraction model’s performance in the long sentences, this paper proposes a capsule network extraction model that combines the shortest dependent path. The approach first detects the shortest dependent path between two drugs in the parse of the original sentence, then applies the Bi-LSTM to obtain the embedding of the original sentence and the shortest dependent path. The embedding are them put into the capsule network, in which the dynamic routing mechanism could dynamically determine the amount of information transmitted and preserve the high-level feature information. The experimental results on the DDIExtraction2013 show that the proposed achieved 1.17% relative increase in F1 value compared with the current best approaches.
关键词
药物关系抽取 /
最短依存路径 /
双向长短期记忆网络 /
胶囊网络
{{custom_keyword}} /
Key words
drug relationship extraction /
shortest dependent path /
bidirectional long short term memory network /
capsule network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Law V, Knox C, Djoumbou Y, et al. DrugBank 4.0: Shedding new light on drug metabolism[J]. Nucleic Acids Research, 2013, 42(D1): D1091-D1097.
[2] Thorn C F, Klein T E, Altman R B. PharmGKB[J]. Methods in Molecular Biology TM, 2005, 311: 179-191.
[3] Segura Bedmar I, Martinez P, Sánchez Cisneros D. The 1st DDIExtraction-2011 challenge task: Extraction of drug-drug Interactions from biomedical texts[C]//Proceedings of the 1st Challenge Task on Drug-Drug Interaction Extraction 2011, 2011(01): 1-9.
[4] Segura Bedmar I, Martínez P, Herrero Zazo M. Semeval-2013 task 9: Extraction of drug-drug interactions from biomedical texts (DDIextraction 2013)[C]//Proceedings of the Association for Computational Linguistics, 2013.
[5] Sabour S, Frosst N, Hinton G E. Dynamic routing between capsules[C]//Proceedings of Advances in Neural Information Processing Systems, 2017: 3856-3866.
[6] Zhao W, Ye J, Yang M, et al. Investigating capsule networks with dynamic routing for text classification[J]. arXiv preprint arXiv: 1804.00538,2018.
[7] Wang Y, Sun A, Han J, et al. Sentiment analysis by capsules[C]//Proceedings of the 2018 World Wide Web Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2018: 1165-1174.
[8] Wang Y, Sun A, Huang M, et al. Aspect-level sentiment analysis using AS-Capsules[C]//Proceedings of the World Wide Web Conference. ACM, 2019: 2033-2044.
[9] Zheng Z, Huang S, Tu Z, et al. Dynamic past and future for neural machine translation[J]. arXiv preprint arXiv: 1904.09646, 2019.
[10] Tari L, Anwar S, Liang S, et al. Discovering drug-drug interactions: A text-mining and reasoning approach based on properties of drug metabolism[J]. Bioinformatics, 2010, 26(18): i547-i553.
[11] Segura-Bedmar I, Martínez P, de Pablo-Sánchez C. A linguistic rule-based approach to extract drug-drug interactions from pharmacological documents[C]//Proceedings of the BMC Bioinformatics. BioMed Central, 2011, 12(2): S1.
[12] He L, Yang Z, Zhao Z, et al. Extracting drug-drug interaction from the biomedical literature using a stacked generalization-based approach[J]. PloS one, 2013, 8(6): e65814.
[13] Rastegar-Mojarad M, Boyce R D, Prasad R. UWM-TRIADS: Classifying drug-drug interactions with two-stage SVM and post-processing[C]//Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval 2013), 2013(2): 667-674.
[14] Kim S, Liu H, Yeganova L, et al. Extracting drug-drug interactions from literature using a rich feature-based linear kernel approach[J]. Journal of Biomedical Informatics, 2015, 55: 23-30.
[15] Chowdhury M F M, Lavelli A. Exploiting the scope of negations and heterogeneous features for relation extraction: A case study for drug-drug interaction extraction[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2013: 765-771.
[16] Yijia Zhang, Hongfei Lin, Zhihao Yang, et al. A single kernel-based approach to extract drug-drug interactions from biomedical literature[J]. PLoS ONE, 2012, 7(11): e48901.
[17] Shengyu L, Buzhou T, Qingcai C, et al. Drug-drug interaction extraction via convolutional neural networks[J]. Computational and Mathematical Methods in Medicine, 2016: 1-8.
[18] Chanqin Q, Lei H, Xiao S, et al. Multichannel convolutional neural network for biological relation Extraction[J]. BioMed Research International, 2016: 1-10.
[19] Kavaluru R, Rios A, Tran T. Extracting drug-drug interactions with word and character-level recurrent neural networks[C]//Proceedings of the 2017 IEEE International Conference on Healthcare Informatics (ICHI). IEEE, 2017: 5-12.
[20] Asada M, Miwa M, Sasaki Y. Extracting drug-drug interactions with attention CNNs[C]//Proceedings of the BioNLP 2017, 2017: 9-18.
[21] Zhou D, Miao L, He Y. Position-aware deep multi-task learning for drug-drug interaction extraction[J]. Artificial Intelligence in Medicine, 2018, 87: 1-8.
[22] Asada M, Miwa M, Sasaki Y. Enhancing drug-drug interaction extraction from Texts by molecular structure information[J]. arXiv preprint arXiv: 1805.05593, 2018.[23] Xu B, Shi X, Zhao Z, et al. Leveraging biomedical resources in biLSTM for drug-drug interaction extraction[J]. IEEE Access, 2018(6): 33432-33439.
[24] Wang W, Yang X, Yang C, et al. Dependency-based long short term memory network for drug-drug interaction extraction[J]. BMC Bioinformatics, 2017, 18(16): 578.
[25] Yi Z, Li S, Yu J, et al. Drug-drug interaction extraction via recurrent neural network with multiple attention layers[C]//Proceedings of the International Conference on Advanced Data Mining and Applications. Springer, Cham, 2017: 554-566.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
四川省重点研发项目(2018GZ0182,2018GZ0253,2019YFS0236)
{{custom_fund}}
PDF(1792 KB)
