Biomedical Event Extraction Using a New Error Detection Learning Approach Based on Neural Network

查看全文 作　　者：Xiaolei [1,2]Ma;Yang [1,2]Lu;Yinan [1]Lu;Zhili [2]Pei;Jichao [3]Liu

机构地区：[1]College of the Computer Science and Technology,Jilin University,Changchun,130012,China;[2]College of the Computer Science and Technology,Inner Mongolia University for Nationalities,Tongliao,028000,China;[3]School of Science and Technology,Yanching Institute of Technology,Langfang,065202,China

出　　处：《Computers, Materials & Continua》索引2020年第5期,共19页

基　　金：This work was supported by the National Natural Science Foundation of China(No.61672301);Jilin Provincial Science&Technology Development(20180101054JC);Science and Technology Innovation Guide Project of Inner Mongolia Autonomous Region of China(2017);Talent Development Fund of Jilin Province(2018). 摘　　要：Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model. 关键词：Biomedical event extraction pair representation error data detection sample identification

相关文献

参考文献（28）
引证文献（3）
耦合文献（0）

参考文献(28)

引证文献(3)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Biomedical Event Extraction Using a New Error Detection Learning Approach Based on Neural Network

参考文献(28)

引证文献(3)

用户提示