{"title":"A comparative study of deep learning approaches for Chinese Sentence Classification","authors":"Zhu Zeng","doi":"10.1109/ICCEAI52939.2021.00045","DOIUrl":null,"url":null,"abstract":"One of the most commonly used natural language processing technologies is text classification. Spam detection, news text classification, information retrieval, emotion analysis, and intention judgment, among other applications, are all popular text classification applications [25]. Text classification is the process of assigning pre-defined class labels to text documents in order to shape semantic classes. Engineering, medical science, life science, social sciences and humanities, marketing, and government are only a few of the real-world applications. Machine learning and deep learning algorithms have recently become common and efficient methods for dealing with text classification problems involving labeled data [26]. The primary goal of text classification is to automatically assign texts to pre-defined categories based on their content. In this study, we will conduct a comparative study of the accuracies of different deep learning methods that include Bidirectional Encoder Representations from Transformers (BERT), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Region-based convolutional neural networks and compare the effectiveness of these deep-learning approaches in classifying Chinese news title text using the THUCNews dataset.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00045","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
One of the most commonly used natural language processing technologies is text classification. Spam detection, news text classification, information retrieval, emotion analysis, and intention judgment, among other applications, are all popular text classification applications [25]. Text classification is the process of assigning pre-defined class labels to text documents in order to shape semantic classes. Engineering, medical science, life science, social sciences and humanities, marketing, and government are only a few of the real-world applications. Machine learning and deep learning algorithms have recently become common and efficient methods for dealing with text classification problems involving labeled data [26]. The primary goal of text classification is to automatically assign texts to pre-defined categories based on their content. In this study, we will conduct a comparative study of the accuracies of different deep learning methods that include Bidirectional Encoder Representations from Transformers (BERT), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Region-based convolutional neural networks and compare the effectiveness of these deep-learning approaches in classifying Chinese news title text using the THUCNews dataset.