基于情感评分的分层文本表示情感分类方法

doi:10.19678/j.issn.1000-3428.0054521

摘要/Abstract

摘要： 文本中的词并非都具有相似的情感倾向和强度，较好地编码上下文并从中提取关键信息对于情感分类任务而言非常重要。为此，提出一种基于情感评分的分层注意力网络框架，以对文本情感进行有效分类。利用双向循环神经网络编码器分别对词向量和句向量进行编码，并通过注意力机制加权求和以获得文档的最终表示。设计辅助网络对文本的词、句进行情感评分，利用该评分调整注意力权重分布。在探究文本的情感信息对分类性能的影响后，通过辅助网络进一步促使模型关注情感色彩强烈的信息。在4个常用情感分类数据集上的实验结果表明，该框架能够关注文本中的情感表达并获得较高的分类准确率。

关键词: 文本表示, 情感分类, 情感计算, 注意力机制, 循环神经网络

Abstract: Not all words in the text have similar sentiment tendency and intensity,so it is very important for sentiment classification tasks that the context is well encoded and the key information is extracted.Therefore,this paper proposes a hierarchical attention network framework based on sentiment evaluation to conduct effective classification for text sentiment.The bidirectional recurrent neural network encoder is used to encode the word vector and sentence vector respectively and the final representation of the text is obtained by the weighted sum of attention mechanism.On this basis,the auxiliary network is designed to evaluate the sentiment of words and sentences.The evaluation score is used to adjust the distribution of attention weight.After exploring the influence of sentiment information of text on classification performance,on the basis of hierarchical representation,the model is further prompted to focus on the information with strong sentiment color through the auxiliary network.Experimental results on four commonly used sentiment classification datasets show that the proposed framework can focus on the sentiment expression in the text and obtain high classification accuracy.

Key words: text representation, sentiment classification, sentiment computing, attention mechanism, Recurrent Neural Network(RNN)

中图分类号:

TP391

胡均毅, 李金龙. 基于情感评分的分层文本表示情感分类方法[J]. 计算机工程, 2020, 46(3): 46-52,59.

HU Junyi, LI Jinlong. Sentiment Evaluation Based Hierarchical Text Representation Method for Sentiment Classification[J]. Computer Engineering, 2020, 46(3): 46-52,59.

https://www.ecice06.com/CN/Y2020/V46/I3/46

图/表 6

20200321084129

20200321084131

20200321084134

20200321084137

20200321084140

20200321084143

参考文献

[1] ISBELL C L.Sparse multi-level representations for text retrieval[M].Cambridge,USA:MIT Press,1998.
[2] WANG Mingqiang,LIU Mengting,FENG Shi,et al.A novel calibrated label ranking based method for multiple emotions detection in Chinese microblogs[M].Berlin,Germany:Springer,2014.
[3] TANG Duyu,QIN Bing,LIU Ting.Document modeling with gated recurrent neural network for sentiment classification[C]//Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing.Washington D.C.,USA:IEEE Press,2015:1422-1432.
[4] RICHARD S,ALEX P,JY W,et al.Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of 2013 Conference on Empirical Methods in Natural Language Processing.Washington D.C.,USA:IEEE Press,2013:1631-1642.
[5] TANG Duyu,WEI Furu,YANG Nan,et al.Learning sentiment specific word embedding for twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.New York,USA:ACM Press,2014:1555-1565.
[6] MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[EB/OL].[2019-03-10].https://arxiv.org/abs/1301.3781.
[7] JEFFREY P,RICHARD S,CHRISTOPHER M.Glove:global vectors for word representation[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing.New York,USA:ACM Press,2014:1532-1543.
[8] TANG Duyu.Sentiment-specific representation learning for document-level sentiment analysis[C]//Proceedings of the 8th ACM International Conference on Web Search and Data Mining.New York,USA:ACM Press,2015:447-452.
[9] RONAN C,JASON W,LEON B,et al.Natural language processing(almost) from scratch[J].Journal of Machine Learning Research,2011,12:2493-2537.
[10] TANG Duyu,WEI Furu,QIN Bing,et al.Building large-scale Twitter-specific sentiment lexicon:a representation learning approach[C]//Proceedings of COLING'14.New York,USA:ACM Press,2014:172-182.
[11] GOTTLOB F.Sense and reference[J].The Philo-sophical Review,1948,57(3):209-230.
[12] ARMAND J,EDOUARD G,PIOTR B,et al.Bag of tricks for efficient text classification[C]//Proceedings of the 15th Conference of EACL.New York,USA:ACM Press,2017:427-431.
[13] JEFFREY L E.Finding structure in time[J].Cognitive Science,1990,14(2):179-211.
[14] ZHENG Bin,YANG Chen,MA Xiaoping,et al.Malignant thyroid nodule detection based on circular convolutional neural network[J].Laser & Optoelectronics Progress,2019,56(24):102-109.(in Chinese) 郑斌,杨晨,马小萍,等.基于循环卷积神经网络的甲状腺恶性结节检测[J].激光与光电子学进展,2019,56(24):102-109.
[15] YOON K.Convolutional neural networks for sentence classification[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing.New York,USA:ACM Press,2014:1746-1751.
[16] ZHANG X,ZHAO J B,LECUN Y.Character-level convolutional networks for text classification[EB/OL].[2019-03-10].http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf.
[17] LAI Siwei,XU Liheng,LIU Kang,et al.Recurrent convolutional neural networks for text classification[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.New York,USA:ACM Press,2015:2267-2273.
[18] ZHOU Jinfeng,YE Shiren,WANG Hui.Text sentiment classification based on deep convolutional neural network model[J].Computer Engineering,2019,45(3):300-308.(in Chinese) 周锦峰,叶施仁,王晖.基于深度卷积神经网络模型的文本情感分类[J].计算机工程,2019,45(3):300-308.
[19] DZMITRY B,KYUNGHYUN C,YOSHUA B.Neural machine translation by jointly learning to align and translate[EB/OL].[2019-03-10].https://de.arxiv.org/pdf/1409.0473.
[20] ASHISH V,NOAM S,NIKI P,et al.Attention is all you need[EB/OL].[2019-03-10].https://arxiv.org/pdf/1706.03762.pdf.
[21] YANG Z C,YANG D Y,DYER C,et al.Hierarchical attention networks for document classification[C]//Proceedings of NAACL'16.New York,USA:ACM Press,2016:1480-1489.
[22] CHEN Huimin,SUN Maosong,TU Cunchao,et al.Neural sentiment classification with user and product attention[C]//Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing.New York,USA:ACM Press,2016:1650-1659.
[23] ZHENG Jianming,GUO Yupu,FENG Chong,et al.A hierarchical neural-network-based document represen-tation approach for text classification[J].Mathematical Problems in Engineering,2018,15:1-10.
[24] ZOU Yicheng,GUI Tao,ZHANG Qi,et al.A lexicon-based supervised attention model for neural sentiment analysis[C]//Proceedings of COLING'18.New York,USA:ACM Press,2018:868-877.
[25] LIU L M,UTIYAMA M,FINCH A,et al.Neural machine translation with supervised attention[C]//Proceedings of COLING'16.New York,USA:ACM Press,2016:3093-3102.
[26] WALAA M,AHMED H,HODA K.Sentiment analysis algorithms and applications:a survey[J].Ain Shams Engineering Journal,2014,5(4):1093-1113.
[27] SAINBAYAR S,JASON W,ROB F,et al.End-to-end memory networks[EB/OL].[2019-03-10].https://arxiv.org/pdf/1610.04211.pdf.
[28] LESLIE N S.Cyclical learning rates for training neural networks[C]//Proceedings of WACV'17.Washington D.C.,USA:IEEE Press,2017:464-472.
[29] LESLIE N S.A disciplined approach to neural network hyper-parameters:part 1-learning rate,batch size,momentum,and weight decay[EB/OL].[2019-03-10].https://arxiv.org/pdf/1803.09820.pdf.
[30] LIAO Xiangwen,WU Xiaojing,GUI Lin,et al.Cross-domain sentiment classification based on representation learning and transfer learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2019,55(1):37-46.(in Chinese)廖祥文,吴晓静,桂林,等.结合表示学习和迁移学习的跨领域情感分类[J].北京大学学报(自然科学版),2019,55(1):37-46.

选择文件类型/文献管理软件名称

选择包含的内容