Open Access Open Access  Restricted Access Subscription Access

Drug-Drug Interaction Extraction via Convolutional Neural Networks


Affiliations
1 Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China
 

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 DDI Extraction 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%.
User
Notifications
Font Size

Abstract Views: 91

PDF Views: 2




  • Drug-Drug Interaction Extraction via Convolutional Neural Networks

Abstract Views: 91  |  PDF Views: 2

Authors

Shengyu Liu
Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China
Buzhou Tang
Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China
Qingcai Chen
Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China
Xiaolong Wang
Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China

Abstract


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 DDI Extraction 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%.