基于统计和基于cnn信息的句子分类

Lang Zhining, Gu Xiaozhuo, Zhou Quan, Xu Taizhong
{"title":"基于统计和基于cnn信息的句子分类","authors":"Lang Zhining, Gu Xiaozhuo, Zhou Quan, Xu Taizhong","doi":"10.1109/ICTAI.2016.0156","DOIUrl":null,"url":null,"abstract":"Sentence classification, serving as the foundation of the subsequent text-based processing, continues attracting researchers attentions. Recently, with the great success of deep learning, convolutional neural network (CNN), a kind of common architecture of deep learning, has been widely used to this filed and achieved excellent performance. However, most CNN-based studies focus on using complex architectures to extract more effective category information, requiring more time in training models. With the aim to get better performance with less time cost on classification, this paper proposes two simple and effective methods by fully combining information both extracted from statistics and CNN. The first method is S-SFCNN, which combines statistical features and CNN-based probabilistic features of classification to build feature vectors, and then the vectors are used to train the logistic regression classifiers. And the second method is C-SFCNN, which combines CNN-based features and statistics-based probabilistic features of classification to build feature vectors. In the two methods, the Naive Bayes log-count ratios are selected as the text statistical features and the single-layer and single channel CNN is used as our CNN architecture. The testing results executed on 7 tasks show that our methods can achieve better performance than many other complex CNN models with less time cost. In addition, we summarized the main factors influencing the performance of our methods though experiment.","PeriodicalId":245697,"journal":{"name":"2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Combining Statistics-Based and CNN-Based Information for Sentence Classification\",\"authors\":\"Lang Zhining, Gu Xiaozhuo, Zhou Quan, Xu Taizhong\",\"doi\":\"10.1109/ICTAI.2016.0156\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Sentence classification, serving as the foundation of the subsequent text-based processing, continues attracting researchers attentions. Recently, with the great success of deep learning, convolutional neural network (CNN), a kind of common architecture of deep learning, has been widely used to this filed and achieved excellent performance. However, most CNN-based studies focus on using complex architectures to extract more effective category information, requiring more time in training models. With the aim to get better performance with less time cost on classification, this paper proposes two simple and effective methods by fully combining information both extracted from statistics and CNN. The first method is S-SFCNN, which combines statistical features and CNN-based probabilistic features of classification to build feature vectors, and then the vectors are used to train the logistic regression classifiers. And the second method is C-SFCNN, which combines CNN-based features and statistics-based probabilistic features of classification to build feature vectors. In the two methods, the Naive Bayes log-count ratios are selected as the text statistical features and the single-layer and single channel CNN is used as our CNN architecture. The testing results executed on 7 tasks show that our methods can achieve better performance than many other complex CNN models with less time cost. In addition, we summarized the main factors influencing the performance of our methods though experiment.\",\"PeriodicalId\":245697,\"journal\":{\"name\":\"2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI)\",\"volume\":\"50 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICTAI.2016.0156\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTAI.2016.0156","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

摘要

句子分类作为后续基于文本处理的基础,一直受到研究者的关注。近年来,随着深度学习的巨大成功,卷积神经网络(CNN)作为一种常见的深度学习架构被广泛应用于该领域,并取得了优异的表现。然而,大多数基于cnn的研究都集中在使用复杂的架构来提取更有效的类别信息,这需要更多的时间来训练模型。为了以更少的时间成本获得更好的分类性能,本文提出了两种简单有效的方法,充分结合了统计数据和CNN提取的信息。第一种方法是S-SFCNN,将统计特征与基于cnn的分类概率特征相结合,构建特征向量,然后用这些特征向量训练逻辑回归分类器。第二种方法是C-SFCNN,将基于cnn的特征与基于统计的分类概率特征相结合,构建特征向量。两种方法均选择朴素贝叶斯对数计数比作为文本统计特征,采用单层单通道CNN作为我们的CNN架构。在7个任务上执行的测试结果表明,我们的方法可以在更少的时间成本下获得比许多其他复杂CNN模型更好的性能。此外,通过实验总结了影响方法性能的主要因素。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Combining Statistics-Based and CNN-Based Information for Sentence Classification
Sentence classification, serving as the foundation of the subsequent text-based processing, continues attracting researchers attentions. Recently, with the great success of deep learning, convolutional neural network (CNN), a kind of common architecture of deep learning, has been widely used to this filed and achieved excellent performance. However, most CNN-based studies focus on using complex architectures to extract more effective category information, requiring more time in training models. With the aim to get better performance with less time cost on classification, this paper proposes two simple and effective methods by fully combining information both extracted from statistics and CNN. The first method is S-SFCNN, which combines statistical features and CNN-based probabilistic features of classification to build feature vectors, and then the vectors are used to train the logistic regression classifiers. And the second method is C-SFCNN, which combines CNN-based features and statistics-based probabilistic features of classification to build feature vectors. In the two methods, the Naive Bayes log-count ratios are selected as the text statistical features and the single-layer and single channel CNN is used as our CNN architecture. The testing results executed on 7 tasks show that our methods can achieve better performance than many other complex CNN models with less time cost. In addition, we summarized the main factors influencing the performance of our methods though experiment.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:481959085
Book学术官方微信