Miller Timothy, Geva Alon, Dligach Dmitriy
Computational Health Informatics Program, Boston Children's Hospital.
Harvard Medical School.
Proc Conf. 2019 Jun;2019:22-27. doi: 10.18653/v1/w19-1903.
In this paper we describe an evaluation of the potential of classical information extraction methods to extract drug-related attributes, including adverse drug events, and compare to more recently developed neural methods. We use the 2018 N2C2 shared task data as our gold standard data set for training. We train support vector machine classifiers to detect drug and drug attribute spans, and pair these detected entities as training instances for an SVM relation classifier, with both systems using standard features. We compare to baseline neural methods that use standard contextualized embedding representations for entity and relation extraction. The SVM-based system and a neural system obtain comparable results, with the SVM system doing better on concepts and the neural system performing better on relation extraction tasks. The neural system obtains surprisingly strong results compared to the system based on years of research in developing features for information extraction.
在本文中，我们描述了对经典信息提取方法提取药物相关属性（包括药物不良事件）潜力的评估，并与最近开发的神经方法进行比较。我们使用2018年N2C2共享任务数据作为训练的黄金标准数据集。我们训练支持向量机分类器来检测药物和药物属性跨度，并将这些检测到的实体配对作为支持向量机关系分类器的训练实例，两个系统均使用标准特征。我们与使用标准上下文嵌入表示进行实体和关系提取的基线神经方法进行比较。基于支持向量机的系统和神经系统获得了可比的结果，支持向量机系统在概念方面表现更好，而神经系统在关系提取任务方面表现更好。与基于多年信息提取特征开发研究的系统相比，神经系统获得了惊人的强大结果。
