Classifying medical relations in clinical text via convolutional neural networks
Classifying medical relations in clinical text via convolutional neural networks
复制标题
DOI：
10.1016/j.artmed.2018.05.001
复制
发表时间：
2019-01-01
影响因子：
7.5
通讯作者：
Dai, Rui
中科院分区：
文献类型：
--
作者：
He, Bin;Guan, Yi;Dai, Rui
关系分类的深度学习研究在通用领域取得了良好的表现。本研究提出了一种具有多池化操作的卷积神经网络（CNN）架构，用于临床记录上的医疗关系分类，并探索了具有类别级约束矩阵的损失函数。使用 2010 i2b2/VA 关系语料库的实验证明了这些模型不依赖于任何外部特征，优于以前的单模型方法，并且我们的最佳模型与现有的基于集成的方法具有竞争力。
Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method.