Abstract

Info

Author(s):: LI Qihang; LIAO Wei; School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

Keywords:: Keywords: biomedical text attention mechanism convolutional neural network recurrent neural network text classification

Abstract:: Abstract: The accurate classification of biomedical texts is an important way to promote the development of hospital information. Herein a two-level text classification model based on attentional mechanism is proposed to effectively classify biomedical texts. The model combines the advantages of convolutional neural network and recurrent neural network to extract features from the disease texts input by users. The context association information in the text is firstly extracted through Bi-GRU channel and Bi-LSTM channel at the first level, and meanwhile, in order to enhance the feature extraction ability of the model, attention mechanism is introduced to this level. After the time series features extracted from the two channels are spliced-together, the spliced-result is input to the second level for further extracting the local features from the text. The final classification results are output by the classifier. The evaluation of the performances in classifying biomedical texts show that compared with baseline models, the proposed model achieves a classification accuracy of 91.45%, with a significant classification performance.