基于Wasserstein距离分层注意力模型的跨域情感分类

doi:10.16451/j.cnki.issn1003-6059.201905007

Abstract
Figure/Table
References (0)
Related Citation (5)

Download: PDF (791 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The task of cross-domain sentiment classification is to analyze the sentiment orientation of the target domain lacking labeled data using the source-domain data with sentiment labels. A hierarchical attention model based on Wasserstein distance is proposed in this paper. The hierarchical model is used for feature extraction by combining attention mechanism, and Wasserstein distance is used as the domain difference metric to automatically capture the domain-sharing features through adversarial training. Further auxiliary task is constructed to capture the domain-special features cooccurring with domain-sharing features. These two kinds of features are united to complete the cross-domain sentiment classification task. The experimental results on Amazon datasets demonstrate that the proposed model achieves a higher accuracy and a better stability on different cross-domain pairs.

Key words： Cross-Domain Sentiment Classification Wasserstein Distance Hierarchical Model Attention Mechanism Bidirectional Gated Recurrent Unit

Received: 03 December 2018

ZTFLH:

TP 391

Fund:Supported by National Key R&D Program of China(No.2018YF
C1900800), Research Program of State Language Commission(No.YB135-89)

Corresponding Authors: (DU Yongping(Corresponding author), Ph.D., associate professor. Her research inte-rests include information retrieval, information extraction and natural language processing.)

About author:: (HE Meng, master student. Her research interests include natural language processing and sentiment analysis.)(ZHAO Xiaozheng, master student. Her research interests include natural language processing and sentiment analysis.)

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	DU Yongping¹
	HE Meng¹
	ZHAO Xiaozheng¹

Cite this article:

DU Yongping¹,HE Meng¹,ZHAO Xiaozheng¹. Wasserstein Distance Based Hierarchical Attention Model for Cross-Domain Sentiment Classification[J]. , 2019, 32(5): 446-454.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201905007 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I5/446

[1] 赵传君,王素格,李德玉,等.基于分组提升集成的跨领域文本情感分类.计算机研究与发展, 2015, 52(3): 629-638.
(ZHAO C J, WANG S G, LI D Y, et al. Cross-Domain Text Sentiment Classification Based on Grouping-AdaBoost Ensemble. Journal of Computer Research and Development, 2015, 52(3): 629-638.)
[2] 庄福振,罗平,何清,等.迁移学习研究进展.软件学报, 2015, 26(1): 26-39.
(ZHUANG F Z, LUO P, HE Q, et al. Survey on Transfer Learning Research. Journal of Software, 2015, 26(1): 26-39.)
[3] PAN S J, YANG Q. A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
[4] 顾鑫,王士同,许敏.基于多源的跨领域数据分类快速新算法.自动化学报, 2014, 40(3): 531-547.
(GU X, WANG S T, XU M. A New Cross-multidomain Classification Algorithm and Its Fast Version for Large Datasets. Acta Automatica Sinica, 2014, 40(3): 531-547.)
[5] BLITZER J, DREDZE M, PEREIA F. Biographies, Bollywood, Boom-Boxes and Blenders: Domain Adaption for Sentiment Classification // Proc of the 45th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2007:440-447.
[6] PAN S J, NI X C, SUN J T, et al. Cross-Domain Sentiment Classification via Spectral Feature Alignment // Proc of the 19th International Conference on World Wide Web. New York, USA: ACM, 2010: 751-760.
[7] SHARMA R, BHATTACHARYYA P, DANDAPAT S, et al. Identifying Transferable Information across Domains for Cross-Domain Sentiment Classification // Proc of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2018: 968-978.
[8] WU F Z, HUANG Y F, YAN J. Active Sentiment Domain Adaptation // Proc of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2017:1701-1711.
[9] GLOROT X, BORDES A, BENGIO Y. Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach // Proc of the 28th International Conference on Machine Learning. Madison, USA: Omnipress, 2011: 513-520.
[10] CHEN M M, XU Z X, WEINBERGER K, et al. Marginalized Denoising Autoencoders for Domain Adaptation // Proc of the 29th International Conference on Machine Learning. Berlin, Germany: Springer, 2012: 767-774.
[11] ZISER Y, REICHART R. Neural Structural Correspondence Lear-ning for Domain Adaptation // Proc of the 21st Conference on Computational Natural Language Learning. Stroudsburg, USA: ACL, 2017: 400-410.
[12] ZISER Y, REICHART R. Pivot Based Language Modeling for Improved Neural Domain Adaption // Proc of the Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technologies. Stroudsburg, USA: ACL, 2018: 1241-1251.
[13] CUI X, AL-BAZZAZ N, BOLLEGALA D, et al. A Comparative Study of Pivot Selection Strategies for Unsupervised Cross-Domain Sentiment Classification. The Knowledge Engineering Review, 2018, 33. DOI:10.1017/S0269888918000085.
[14] GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-Adversarial Training of Neural Networks. Journal of Machine Learning Research, 2015, 17: 2096-2030.
[15] YU J F, JIANG J. Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification // Proc of the 8th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2017: 654-663.
[16] LI Z, ZHANG Y, WEI Y, et al. End-to-End Adversarial Memory Network for Cross-Domain Sentiment Classification // Proc of the 26th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2017: 2237-2243.
[17] LI Z, WEI Y, ZHANG Y, et al. Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification[C/OL]. [2018-11-15]. https://www.cse.ust.hk/~yuzhangcse/papers/Li_Wei_Zhang_Yang_AAAI18.pdf.
[18] TANG D Y, QIN B, LIU T. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 1422-1432.
[19] ZHOU P, SHI W, TIAN J, et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification // Proc of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2016: 207-212.
[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[C/OL]. [2018-11-15]. https://arxiv.org/pdf/1706.03762.pdf.
[21] MARTIN A, CHINTALA S, BOTTOU L. Wasserstein Gan[C/OL]. [2018-11-15]. https://arxiv.org/pdf/ 1701.07875.pdf.
[22] GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved Training of Wasserstein GANs[C/OL]. [2018-11-15]. https://arxiv.org/pdf/1704.00028.pdf.
[23] YU J F, JIANG J. Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 236-246.