CFSE: a Chinese short text classification method based on character frequency sub-word enhancement

IF 3.2 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Connection Science Pub Date : 2023-10-06 DOI:10.1080/09540091.2023.2263663

Xingguang Wang, Shunxiang Zhang, Zichen Ma, Yunduo Liu, Youqiang Zhang

{"title":"CFSE: a Chinese short text classification method based on character frequency sub-word enhancement","authors":"Xingguang Wang, Shunxiang Zhang, Zichen Ma, Yunduo Liu, Youqiang Zhang","doi":"10.1080/09540091.2023.2263663","DOIUrl":null,"url":null,"abstract":"As a foundation task of natural language processing, text classification is widely used in information retrieval, public opinion analysis, and other related tasks. Facing the problem of sparse features of Chinese short texts, which affects the classification accuracy of Chinese short texts, this paper proposes a Chinese short text classification method based on the Character Frequency Sub-word Enhancement (CFSE), which can effectively improve the classification accuracy of Chinese short texts. First, the initial Chinese-character sequence is mapped to the corresponding Character Frequency Sub-word (CFS) sequence based on the global character1 frequency information. Second, the relationship features among data are extracted based on BiLSTM-Att processing CFS sequence, and the semantic features of the initial Chinese-character sequence are obtained through ERNIE. Finally, these two kinds of features are fused and input into the text classifier to obtain the classification results. Experimental results show that the proposed method can improve the classification accuracy of Chinese short texts.","PeriodicalId":50629,"journal":{"name":"Connection Science","volume":"41 1","pages":"0"},"PeriodicalIF":3.2000,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Connection Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/09540091.2023.2263663","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

As a foundation task of natural language processing, text classification is widely used in information retrieval, public opinion analysis, and other related tasks. Facing the problem of sparse features of Chinese short texts, which affects the classification accuracy of Chinese short texts, this paper proposes a Chinese short text classification method based on the Character Frequency Sub-word Enhancement (CFSE), which can effectively improve the classification accuracy of Chinese short texts. First, the initial Chinese-character sequence is mapped to the corresponding Character Frequency Sub-word (CFS) sequence based on the global character1 frequency information. Second, the relationship features among data are extracted based on BiLSTM-Att processing CFS sequence, and the semantic features of the initial Chinese-character sequence are obtained through ERNIE. Finally, these two kinds of features are fused and input into the text classifier to obtain the classification results. Experimental results show that the proposed method can improve the classification accuracy of Chinese short texts.

查看原文本刊更多论文

基于字符频率子词增强的中文短文本分类方法

文本分类作为自然语言处理的基础任务，广泛应用于信息检索、舆情分析等相关任务中。针对中文短文本特征稀疏影响中文短文本分类精度的问题，本文提出了一种基于字符频率子词增强(CFSE)的中文短文本分类方法，可以有效地提高中文短文本的分类精度。首先，基于全局字符1频率信息，将初始汉字序列映射到相应的字符频率子词(CFS)序列;其次，基于BiLSTM-Att处理的CFS序列提取数据间的关系特征，并通过ERNIE获得初始汉字序列的语义特征;最后，将这两种特征融合并输入到文本分类器中，得到分类结果。实验结果表明，该方法可以提高中文短文本的分类准确率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Connection Science 工程技术-计算机：理论方法

CiteScore

6.50

自引率

39.60%

发文量

审稿时长

3 months

期刊介绍： Connection Science is an interdisciplinary journal dedicated to exploring the convergence of the analytic and synthetic sciences, including neuroscience, computational modelling, artificial intelligence, machine learning, deep learning, Database, Big Data, quantum computing, Blockchain, Zero-Knowledge, Internet of Things, Cybersecurity, and parallel and distributed computing. A strong focus is on the articles arising from connectionist, probabilistic, dynamical, or evolutionary approaches in aspects of Computer Science, applied applications, and systems-level computational subjects that seek to understand models in science and engineering.