Biomedical event trigger detection by dependency-based word embedding. Issue 2 (August 2016)

• Record Type: Journal Article
• Authors: Wang, Jian; Zhang, Jianhai; An, Yuan; Lin, Hongfei; Yang, Zhihao; Zhang, Yijia; Sun, Yuanyuan
• Is Part Of: BMC medical genomics. Volume 9:Issue 2(2016)
• Page Start: 123
• Page End: 133
• Publication Date: 2016-08
• Subjects: Biomedical event extraction -- Trigger detection -- Dependency-based word embedding -- Neural network; Medical genetics -- Periodicals; Genomics -- Periodicals; 616.042
• DOI: 10.1186/s12920-016-0203-8
• Languages: English
• ISSNs: 1755-8794

Abstract

Abstract Background In biomedical research, events revealing complex relations between entities play an important role. Biomedical event trigger identification has become a research hotspot since its important role in biomedical event extraction. Traditional machine learning methods, such as support vector machines (SVM) and maxent classifiers, which aim to manually design powerful features fed to the classifiers, depend on the understanding of the specific task and cannot generalize to the new domain or new examples. Methods In this paper, we propose an approach which utilizes neural network model based on dependency-based word embedding to automatically learn significant features from raw input for trigger classification. First, we employ Word2vecf, the modified version of Word2vec, to learn word embedding with rich semantic and functional information based on dependency relation tree. Then neural network architecture is used to learn more significant feature representation based on raw dependency-based word embedding. Meanwhile, we dynamically adjust the embedding while training for adapting to the trigger classification task. Finally, softmax classifier labels the examples by specific trigger class using the features learned by the model. Results The experimental results show that our approach achieves a micro-averaging F1 score of 78.27 and a macro-averaging F1 score of 76.94 % in significant trigger classes, and performs better than baseline methods. In addition, we can achieve the semantic distributed representation of every trigger word.