A convolutional attentional neural network for sentiment classification

Jiachen Du, Lin Gui, Yulan He, Ruifeng Xu
{"title":"A convolutional attentional neural network for sentiment classification","authors":"Jiachen Du, Lin Gui, Yulan He, Ruifeng Xu","doi":"10.1109/SPAC.2017.8304320","DOIUrl":null,"url":null,"abstract":"Neural network models with attention mechanism have shown their efficiencies on various tasks. However, there is little research work on attention mechanism for text classification and existing attention model for text classification lacks of cognitive intuition and mathematical explanation. In this paper, we propose a new architecture of neural network based on the attention model for text classification. In particular, we show that the convolutional neural network (CNN) is a reasonable model for extracting attentions from text sequences in mathematics. We then propose a novel attention model base on CNN and introduce a new network architecture which combines recurrent neural network with our CNN-based attention model. Experimental results on five datasets show that our proposed models can accurately capture the salient parts of sentences to improve the performance of text classification.","PeriodicalId":161647,"journal":{"name":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SPAC.2017.8304320","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

Abstract

Neural network models with attention mechanism have shown their efficiencies on various tasks. However, there is little research work on attention mechanism for text classification and existing attention model for text classification lacks of cognitive intuition and mathematical explanation. In this paper, we propose a new architecture of neural network based on the attention model for text classification. In particular, we show that the convolutional neural network (CNN) is a reasonable model for extracting attentions from text sequences in mathematics. We then propose a novel attention model base on CNN and introduce a new network architecture which combines recurrent neural network with our CNN-based attention model. Experimental results on five datasets show that our proposed models can accurately capture the salient parts of sentences to improve the performance of text classification.
一种用于情感分类的卷积注意神经网络
具有注意机制的神经网络模型在各种任务上都显示出其有效性。然而,关于文本分类注意机制的研究很少,现有的文本分类注意模型缺乏认知直觉和数学解释。本文提出了一种基于注意力模型的神经网络文本分类新架构。特别是,我们证明了卷积神经网络(CNN)是一种合理的数学模型,用于从文本序列中提取注意。然后,我们提出了一种新的基于CNN的注意力模型,并引入了一种将递归神经网络与我们基于CNN的注意力模型相结合的新网络架构。在5个数据集上的实验结果表明,我们提出的模型能够准确地捕获句子的显著部分,从而提高文本分类的性能。
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信