结合语义和依存关系的药物相互作用关系抽取  

Drug-drug Interaction Extraction Combining Semantics and Dependency

作　　者：罗熹[1,2] 曾智颖 王建新[1] 安莹[3] LUO Xi;ZENG Zhiying;WANG Jianxin;AN Ying(School of Computer Science and Engineering,Central South University,Changsha 410075,China;Key Laboratory of Network Crime Investigation of Hunan Provincial Colleges,Hunan Police Academy,Changsha 410138,China;Big Data Institute,Central South University,Changsha 410083,China)

机构地区：[1]中南大学计算机学院,湖南长沙410083 [2]湖南警察学院网络犯罪侦查湖南省普通高校重点实验室,湖南长沙410138 [3]中南大学大数据研究院,湖南长沙410083

出　　处：《湖南大学学报（自然科学版）》2022年第6期90-100,共11页Journal of Hunan University:Natural Sciences

基　　金：湖南省自然科学基金项目(2018JJ2534);网络犯罪侦查湖南省普通高校重点实验室开放基金项目(2020WLFZZC003);国家重点研发计划项目(2016YFC0901705)。

摘　　要：从生物医学文本中抽取药物相互作用对可以快速更新药物数据库,具有非常重要的意义与医学应用价值.现有的神经网络模型往往仅从句子序列或其他外部信息中学习到单一片面的特征,难以充分挖掘句中潜在的长距离依赖特征获得全面的特征表示.本文提出一种结合语义和依存关系的药物相互作用关系抽取方法,该方法在利用Bi-GRU网络分别从句子序列和目标药物实体的最短依存路径序列中学习语义特征表示的同时,进一步结合多头自注意力机制挖掘单词之间潜在的依存关系,通过充分融合多源特征来有效提升生物医学文本中药物相互作用对的识别和抽取性能.在DDIExtraction-2013数据集上的实验结果表明,该方法超过现有的药物相互关系抽取方法获得了75.82%的F1值.Automatically extracting unknown drug-drug interactions from biomedical literature can update the drug database quickly,which is of great importance and medical value in application. Existing neural network models often can only learn a single one-sided feature in a certain aspect from sentence sequences or other external information,but it is difficult to fully mine the potential long-distance dependency features from sentences to obtain a comprehensive feature representation. This paper proposes a novel drug-drug interaction extraction method combining semantics and dependency. In this method,we not only use the Bi-GRU network to learn the semantic feature representation from the sentence sequence and the shortest dependency path of the target drug entities,but also combine the multi-head self-attention mechanism to further capture the potential dependencies between words. Finally,these multi-source features are fully fused to effectively improve the performance of drug-drug interaction extraction.The experimental results on the DDIExtraction-2013 dataset show that our method outperforms other existing methods and obtains an F1 value of 75.82%.

关 键 词：药物相互作用 关系抽取 循环神经网络 多头自注意力机制 最短依存路径 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]