多头注意力记忆网络的对象级情感分类

doi:10.16451/j.cnki.issn1003-6059.201911004

Abstract
Figure/Table
References
Related Citation (13)

Download: PDF (711 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract A fine-grained sentiment classification task is to identify the opinion words with the highest degree of correlation with target words and classify the emotional polarity in the text. A deep memory network with multiple-head attention mechanism for aspect level sentiment classification is introduced. The word embedding vector of the text is stored in the memory component, and the multi-head attention mechanism is employed to simultaneously model the overall semantics of the text and the object-related semantics among the multiple feature spaces. A feedforward network layer is applied to integrate the information in multiple feature spaces as a classification feature. Experiments on SemEval-2014 dataset and the extended dataset show that the proposed method is beneficial to alleviate the selective preference of the model.

Key words： Text Sentiment Classification Fine-Grained Sentiment Analysis Attention Mechanism Memory Neural Network

Received: 30 April 2019

ZTFLH:

TP 183

Fund:Supported by National Natural Science Foundation of China(No.4187752)

Corresponding Authors: ZHANG Xinsheng, Ph.D., professor. His research interests include pattern recognition and intelligent information processing.

About author:: GAO Teng, master student. His research interests include sentiment analysis and text mining.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Xingsheng
	GAO Teng

Cite this article:

ZHANG Xingsheng,GAO Teng. Aspect Level Sentiment Classification with Multiple-Head Attention Memory Network[J]. , 2019, 32(11): 997-1005.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201911004 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I11/997

[1] HU M Q, LIU B. Mining and Summarizing Customer Reviews // Proc of the 10th ACM SIGKDD International Conference on Know-ledge Discovery and Data Mining. New York, USA: ACM, 2004: 168-177.
[2] KIM S M, HOVY E. Automatic Detection of Opinion Bearing Words and Sentences[C/OL]. [2019-03-25]. http://soominpantel.com/Download/Papers/2005/ijcnlp_cameraready_letter.pdf.
[3] KIRITCHENKO S, ZHU X D, CHERRY C, et al. NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews // Proc of the 8th International Workshop on Semantic Evaluation. Berlin, Germany: Springer, 2014: 437-442.
[4] 杨爽,陈芬.基于SVM多特征融合的微博情感多级分类研究.数据分析与知识发现, 2017, 1(2): 73-79.
(YANG S, CHEN F. Analyzing Sentiments of Micro-blog Posts Based on Support Vector Machine. Data Analysis and Know-ledge Discovery, 2017, 1(2): 73-79.)
[5] KIM Y. Convolutional Neural Networks for Sentence Classification[C/OL]. [2019-03-25]. http://de.arxiv.org/pdf/1408.5882.
[6] SOCHER R, PERELYGIN A, WU J Y, et al. Recursive Deep Models for Semantic Compositionality over a Sentiment Treebank[C/OL]. [2019-03-25].https://nlp.stanford.edu/pubs/SocherEtAl_EMNLP2013.pdf.
[7] DONG L, WEI F R, TAN C Q, et al. Adaptive Recursive Neural Network for Target-Dependent Twitter Sentiment Classification // Proc of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2014: 49-54.
[8] NGUYEN T H, SHIRAI K. PhraseRNN: Phrase Recursive Neural Network for Aspect-Based Sentiment Analysis // Proc of the Confe-rence on Empirical Methods in Natural Language Processing. Strouds-burg, USA: ACL, 2015: 2509-2514.
[9] HUANG Z H, XU W, YU K. Bidirectional LSTM-CRF Models for Sequence Tagging[C/OL]. [2019-03-25]. https://arxiv.org/pdf/1508.01991.pdf.
[10] TANG D Y, QIN B, FENG X C, et al. Effective LSTMs for Target-Dependent Sentiment Classification // Proc of the 26th International Conference on Computational Linguistics. Berlin, Germany: Springer, 2016: 3298-3307.
[11] MA D H, LI S J, ZHANG X D, et al. Interactive Attention Networks for Aspect-Level Sentiment Classification // Proc of the 26th International Joint Conference on Artificial Intelligence. Berlin, Germany: Springer, 2017: 4068-4074.
[12] WANG Y Q, HUANG M L, ZHAO L Y, et al. Attention-Based LSTM for Aspect-Level Sentiment Classification // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 606-615.
[13] 杜慧,俞晓明,刘悦,等.融合词性和注意力的卷积神经网络对象级情感分类方法.模式识别与人工智能, 2018, 31(12): 1120-1126.
(DU H, YU X M, LIU Y,et al.CNN with Part-of-Speech and Attention Mechanism for Targeted Sentiment Classification. Pattern Recognition and Artificial Intelligence, 2018, 31(12): 1120-1126.)
[14] VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need // Proc of the 31st Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 5998-6008.
[15] SUKHBAATAR S, WESTON J, FERGUS R. End-to-End Memory Networks // Proc of the 29th Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2015: 2440-2448.
[16] TANG D Y, QIN B, LIU T. Aspect Level Sentiment Classification with Deep Memory Network // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 214-224,
[17] BA J L, KIROS J R, HINTON G E. Layer Normalization[C/OL]. [2019-03-25]. https://arxiv.org/pdf/1607.06450.pdf.
[18] PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. SemEval-2014 Task 4: Aspect Based Sentiment Analysis // Proc of the International Conference on Computational Linguistics. Stroudsburg, USA: ACL, 2014: 27-35.
[19] PENNINGTON J, SOCHER R, MANNING C. GloVe: Global Vectors for Word Representation // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2014: 1532-1543.
[20] CHEN P, SUN Z Q, BING L D, et al. Recurrent Attention Network on Memory for Aspect Sentiment Analysis // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2017: 452-461.