Advertisement

Jointly Learning Bilingual Sentiment and Semantic Representations for Cross-Language Sentiment Classification

  • Huiwei ZhouEmail author
  • Yunlong Yang
  • Zhuang Liu
  • Yingyu Lin
  • Pengfei Zhu
  • Degen Huang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10390)

Abstract

Cross-language sentiment classification (CLSC) aims at leveraging the semantic and sentiment knowledge in a resource-abundant language (source language) for sentiment classification in a resource-scarce language (target language). This paper proposes an approach to jointly learning bilingual semantic and sentiment representations (BSSR) for English-Chinese CLSC. First, two neural networks are adopted to learn sentence-level sentiment representations in English and Chinese views respectively, which are attached to all word semantic representations in the corresponding sentence to express the words in the certain sentiment context. Then, another two neural networks in two views are designed to jointly learn BSSR of the document from word representations concatenated with their sentence-level sentiment representations. The proposed approach could capture rich sentiment and semantic information in BSSR learning process. Experiments on NLP&CC 2013 CLSC dataset show that our approach is competitive with the state-of-the-art results.

Keywords

Jointly learning Cross-language Sentiment classification 

Notes

Acknowledgements

This research is supported by Natural Science Foundation of China (No. 61272375).

References

  1. 1.
    Turney, P.D.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of ACL, USA, pp. 417–424 (2002)Google Scholar
  2. 2.
    Tang, D.Y., Wei, F.R., Yang, N., Zhou, M., Liu, T., Qin, B.: Learning sentiment-specific word embedding for twitter sentiment classification. In: Proceeding of ACL, USA, pp. 1555–1565 (2014)Google Scholar
  3. 3.
    Tang, D.Y., Qin, B., Feng, X.C., Liu, T.: Effective LSTMs for target-dependent sentiment classification. In: Proceeding of COLING, Japan, pp. 3298–3307 (2016)Google Scholar
  4. 4.
    Li, S., Wang, R., Liu, H., Huang, C.R.: Active learning for cross-lingual sentiment classification. In: Zhou, G., Li, J., Zhao, D., Feng, Y. (eds.) NLPCC 2013. Communications in Computer and Information Science, vol. 400, pp. 236–246. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-41644-6_22 CrossRefGoogle Scholar
  5. 5.
    Wan, X.J.: Co-training for cross-lingual sentiment classification. In: Proceedings of ACL, Singapore, pp. 235–243 (2009)Google Scholar
  6. 6.
    Chen, Q., Li, W.J., Lei, Y., Liu, X.L., He, Y.X.: Learning to adapt credible knowledge in cross-lingual sentiment analysis. In: Proceedings of ACL, China, pp. 419–429 (2015)Google Scholar
  7. 7.
    Chander, S., Lauly, S., Larochelle, H., et al.: An autoencoder approach to learning bilingual word representations. In: Proceeding of NIPS, Canada, pp. 1853–1861 (2014)Google Scholar
  8. 8.
    Yoshikawa, Y.Y., Iwata, T., Sawada, H., Yamada, T.: Cross-domain matching for bag-of-words data via kernel embeddings of latent distributions. In: Proceedings of NIPS, Canada, pp. 1405–1413 (2015)Google Scholar
  9. 9.
    Rajendran, J., Khapra, M., Chandar, S., Ravindran, B.: Bridge correlational neural networks for multilingual multimodal representation learning (2015). arXiv preprint arXiv:1510.03519
  10. 10.
    Tang, X.W., Wan, X.J.: Learning bilingual embedding model for cross-language sentiment classification. In: the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technologies, pp. 134–141 (2014)Google Scholar
  11. 11.
    Zhou, H.W., Chen, L., Shi, F.L., Huang, D.G.: Learning bilingual sentiment word embeddings for cross-language sentiment classification. In: Proceedings of ACL, China, pp. 430–440 (2015)Google Scholar
  12. 12.
    Klementiev, A., Ivan, T., Bhattarai, B.: Inducing cross lingual distributed representations of words. In: Proceedings of COLING, Indiana, pp. 1459–1474 (2012)Google Scholar
  13. 13.
    Jain, S., Batra, S.: Cross-lingual sentiment analysis using modified BRAE. In: Proceedings of EMNLP, Portugal, pp. 159–168 (2015)Google Scholar
  14. 14.
    Zhou, X.J., Wan, X.J., Xiao, J.G.: Cross-lingual sentiment classification with bilingual document representation learning. In: Proceedings of ACL, Germany, pp. 1403–1412 (2016)Google Scholar
  15. 15.
    Zhou, X.J, Wan, X.J and Xiao, J.G.: Attention-based LSTM network for cross-lingual sentiment classification. In: Proceedings of EMNLP, USA, pp. 247–256 (2016)Google Scholar
  16. 16.
    Collobert, R., Weston, J., Bottou, L., et al.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)zbMATHGoogle Scholar
  17. 17.
    Wang, X., Liu, Y.C., Sun, C.J., Wang, B.X., Wang, X.L.: Predicting polarities of tweets by composing word embeddings with long short-term memory. In: Proceedings of ACL, China, pp. 1343–1353 (2015)Google Scholar
  18. 18.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  19. 19.
    Gers, F.A., Schmidhuber, J.: Recurrent nets that time and count. In: The IEEE-Inns-Enns International Joint Conference on Neural Networks, vol. 3, pp. 189–194 (2000)Google Scholar
  20. 20.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. Int. J. Comput. Appl. 7(5), 347–354 (2005)Google Scholar
  21. 21.
    Xu, L.H., Lin, H.F., Pan, Y., Ren, H., Chen, J.M.: Constructing the affective lexicon ontology. J. China Soc. Sci. Tech. Inf. 27(2), 180–185 (2008)Google Scholar
  22. 22.
    Bastien, F., Lamblin, P., Pascanu, R., et al.: Theano: new features and speed improvements (2012). arXiv preprint arXiv:1211.5590
  23. 23.
    Pennington, B., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of EMNLP, USA, pp. 1532–1543 (2014)Google Scholar
  24. 24.
    Gui, L., Lu, Q., Xu, R., Wei, Q., Cao, Y.: Improving transfer learning in cross lingual opinion analysis through negative transfer detection. In: Zhang, S., Wirsing, M., Zhang, Z. (eds.) KSEM 2015. LNCS, vol. 9403, pp. 394–406. Springer, Cham (2015). doi: 10.1007/978-3-319-25159-2_36 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Huiwei Zhou
    • 1
    Email author
  • Yunlong Yang
    • 1
  • Zhuang Liu
    • 1
  • Yingyu Lin
    • 1
  • Pengfei Zhu
    • 1
  • Degen Huang
    • 1
  1. 1.School of Computer Science and TechnologyDalian University of TechnologyDalianChina

Personalised recommendations