Cross-Domain Sentiment Classification by Capsule Network With Semantic Rules

Sentiment analysis is an important but challenging task. Remarkable success has been achieved on domains where sufficient labeled training data is available. Nevertheless, annotating sufficient data is labor-intensive and time-consuming, establishing significant barriers for adapting the sentiment classification systems to new domains. In this paper, we introduce a Capsule network for sentiment analysis in domain adaptation scenario with semantic rules (CapsuleDAR). CapsuleDAR exploits capsule network to encode the intrinsic spatial part-whole relationship constituting domain invariant knowledge that bridges the knowledge gap between the source and target domains. Furthermore, we also propose a rule network to incorporate the semantic rules into the capsule network to enhance the comprehensive sentence representation learning. Extensive experiments are conducted to evaluate the effectiveness of the proposed CapsuleDAR model on a real world data set of four domains. Experimental results demonstrate that CapsuleDAR achieves substantially better performance than the strong competitors for the cross-domain sentiment classification task.

[1]  Geoffrey E. Hinton,et al.  Transforming Autoencoders , 2011 .

[2]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[3]  Yang Jin,et al.  Capsule Network Performance on Complex Data , 2017, ArXiv.

[4]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[5]  Xiaohua Hu,et al.  Linking Heterogeneous Input Features with Pivots for Domain Adaptation , 2015, IJCAI.

[6]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[7]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[8]  Geoffrey E. Hinton,et al.  Matrix capsules with EM routing , 2018, ICLR.

[9]  K. P. Chow,et al.  Learning Domain-specific Sentiment Lexicon with Supervised Sentiment-aware LDA , 2014, ECAI.

[10]  Yuji Matsumoto,et al.  Transfer Learning for Multiple-Domain Sentiment Analysis - Identifying Domain Dependent/Independent Word Polarity , 2011, AAAI.

[11]  Roi Reichart,et al.  Pivot Based Language Modeling for Improved Neural Domain Adaptation , 2018, NAACL.

[12]  Nigel Collier,et al.  Sentiment Analysis using Support Vector Machines with Diverse Information Sources , 2004, EMNLP.

[13]  Huang Zou,et al.  Sentiment Classification Using Machine Learning Techniques with Syntax Features , 2015, 2015 International Conference on Computational Science and Computational Intelligence (CSCI).

[14]  Rui Xia,et al.  Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification , 2013, IEEE Intelligent Systems.

[15]  Roi Reichart,et al.  Neural Structural Correspondence Learning for Domain Adaptation , 2016, CoNLL.

[16]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[17]  K. P. Chow,et al.  A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon , 2014, ACL.

[18]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[19]  Hongbo Xu,et al.  Adapting Naive Bayes to Domain Adaptation for Sentiment Analysis , 2009, ECIR.

[20]  Qiang Liu,et al.  An Optimization View on Dynamic Routing Between Capsules , 2018, ICLR.

[21]  Qiang Yang,et al.  Cross-domain sentiment classification via spectral feature alignment , 2010, WWW '10.

[22]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[23]  Yu Zhang,et al.  End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification , 2017, IJCAI.

[24]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[25]  Yi Yang,et al.  Fast Easy Unsupervised Domain Adaptation with Marginalized Structured Dropout , 2014, ACL.

[26]  Min Yang,et al.  Investigating Capsule Networks with Dynamic Routing for Text Classification , 2018, EMNLP.

[27]  Gong Ling,et al.  An improved TF-IDF approach for text classification , 2005 .

[28]  Xiaoyan Zhu,et al.  Sentiment Analysis by Capsules , 2018, WWW.

[29]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[30]  K. P. Chow,et al.  LCCT: A Semi-supervised Model for Sentiment Classification , 2015, NAACL.

[31]  Kilian Q. Weinberger,et al.  Marginalized Denoising Autoencoders for Domain Adaptation , 2012, ICML.

[32]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[33]  Gabriela Csurka,et al.  A Domain Adaptation Regularization for Denoising Autoencoders , 2016, ACL.

[34]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[35]  Nikos Mamoulis,et al.  Investment Recommendation using Investor Opinions in Social Media , 2016, SIGIR.