Drug-Drug Interaction Extraction via Convolutional Neural Networks.
Drug-Drug Interaction Extraction via Convolutional Neural Networks.
复制标题
通过卷积神经网络提取药物相互作用
DOI：
10.1155/2016/6918381
复制
发表时间：
2016
影响因子：
--
通讯作者：
Wang X
中科院分区：
文献类型：
--
作者：
Liu S;Tang B;Chen Q;Wang X
药物间相互作用抽取作为自然语言处理中一个典型的关系抽取任务，一直受到人们的关注。大多数国家的最先进的DDI提取系统是基于支持向量机（SVM）与大量的手动定义的功能。最近，卷积神经网络（CNN），一个强大的机器学习方法，几乎不需要手动定义的功能，已经表现出巨大的潜力，许多NLP任务。值得使用CNN进行DDI提取，这从未被研究过。提出了一种基于CNN的DDI提取方法。在2013年DDIExtraction挑战语料库上进行的实验表明，CNN是DDI提取的好选择。基于CNN的DDI提取方法的F分数为69.75%，比现有的最佳性能方法高出2.75%。
Drug-drug interaction (DDI) extraction as a typical relation extraction task in natural language processing (NLP) has always attracted great attention. Most state-of-the-art DDI extraction systems are based on support vector machines (SVM) with a large number of manually defined features. Recently, convolutional neural networks (CNN), a robust machine learning method which almost does not need manually defined features, has exhibited great potential for many NLP tasks. It is worth employing CNN for DDI extraction, which has never been investigated. We proposed a CNN-based method for DDI extraction. Experiments conducted on the 2013 DDIExtraction challenge corpus demonstrate that CNN is a good choice for DDI extraction. The CNN-based DDI extraction method achieves an F-score of 69.75%, which outperforms the existing best performing method by 2.75%.