Vietnamese POS Tagging for Social Media Text

  • Ngo Xuan BachEmail author
  • Nguyen Dieu Linh
  • Tu Minh Phuong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9949)


This paper presents an empirical study on Vietnamese part-of-speech (POS) tagging for social media text, which shows several challenges compared with tagging for general text. Social media text does not always conform to formal grammars and correct spelling. It also uses abbreviations, foreign words, and icons frequently. A POS tagger developed for conventional, edited text would perform poorly on such noisy data. We address this problem by proposing a tagging model based on Conditional random fields with various kinds of features for Vietnamese social media text. We introduce a corpus for POS tagging, which consists of more than four thousands sentences from Facebook, the most popular social network in Vietnam. Using this corpus, we performed a series of experiments to evaluate the proposed model. Our model achieved 88.26 % tagging accuracy, which is 11.27 % improvement over a state-of-the-art Vietnamese POS tagger developed for general, conventional text.


Part-of-Speech tagging Social media text Conditional Random Fields 



This work was partially supported by “2016 PTIT Research Grant”, Posts and Telecommunications Institute of Technology, Vietnam. We also would like to thank FPT for financial support which made this work possible.


  1. 1.
    Albogamy, F., Ramsay, A.: POS tagging for Arabic tweets. In: Proceedings of RANLP, pp. 1–8 (2015)Google Scholar
  2. 2.
    Aldarmaki, H., Diab, M.: Robust part-of-speech tagging of Arabic text. In: Proceedings of the 2nd Workshop on Arabic NLP, pp. 173–182 (2015)Google Scholar
  3. 3.
    Bach, N.X., Hiraishi, K., Minh, N.L., Shimazu, A.: Dual decomposition for Vietnamese part-of-speech tagging. In: Proceedings of KES, pp. 123–131 (2013)Google Scholar
  4. 4.
    Brill, E.: Transformation-based error-driven learning and natural language processing: a case study in part of speech tagging. Comput. Linguist. 21(4), 543–565 (1995)MathSciNetGoogle Scholar
  5. 5.
    Gimpel, K., Schneider, N., O’Connor, B., Das, D., Mills, D., Eisenstein, J., Heilman, M., Yogatama, D., Flanigan, J., Smith, N.A.: Part-of-speech tagging for twitter: annotation, features, and experiments. In: Proceedings of ACL, pp. 42–47 (2011)Google Scholar
  6. 6.
    Kawahara, D., Kurohashi, S., Hasida, K.: Construction of a Japanese relevance-tagged corpus. In: Proceedings of LREC, pp. 2008–2013 (2002)Google Scholar
  7. 7.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of ICML, pp. 282–289 (2001)Google Scholar
  8. 8.
    Le, H.P., Roussanaly, A., Nguyen, T.M.H., Rossignol, M.: An empirical study of maximum entropy approach for part-of-speech tagging of Vietnamese texts. In: Proceedings of TALN (2010)Google Scholar
  9. 9.
    Li, Z., Zhang, M., Che, W., Liu, T., Chen, W., Li, H.: Joint models for Chinese POS tagging and dependency parsing. In: Proceedings of EMNLP, pp. 1180–1191 (2011)Google Scholar
  10. 10.
    Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of English: the Penn Treebank. Comput. Linguist. 19(2), 313–330 (1993)Google Scholar
  11. 11.
    Nakagawa, T., Kudo, T., Matsumoto, Y.: Revision learning and its application to part-of-speech tagging. In: Proceedings of ACL, pp. 497–450 (2002)Google Scholar
  12. 12.
    Nakagawa, T., Uchimoto, K.: A hybrid approach to word segmentation and POS tagging. In: Proceedings of ACL, pp. 217–220 (2007)Google Scholar
  13. 13.
    Neunerdt, M., Trevisan, B., Reyer, M., Mathar, R.: Part-of-speech tagging for social media texts. In: Gurevych, I., Biemann, C., Zesch, T. (eds.) GSCL. LNCS, vol. 8105, pp. 139–150. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  14. 14.
    Nghiem, M., Dinh, D., Nguyen, M.: Improving Vietnamese POS tagging by integrating a rich feature set and support vector machines. In: Proceedings of RIVF, pp. 128–133 (2008)Google Scholar
  15. 15.
    Nguyen, P.T., Vu, X.L., Nguyen, T.M.H., Nguyen, V.H., Le, H.P.: Building a large syntactically-annotated corpus of Vietnamese. In: Proceedings of the Third Linguistic Annotation Workshop, ACL-IJCNLP, pp. 182–185 (2009)Google Scholar
  16. 16.
    Nguyen, L.M., Xuan, B.N., Viet, C.N., Nhat, M.P.Q., Shimazu, A.: A semi-supervised learning method for Vietnamese part-of-speech tagging. In: Proceedings of KSE, pp. 141–146 (2010)Google Scholar
  17. 17.
    Owoputi, O., O’Connor, B., Dyer, C., Gimpel, K., Schneider, N., Smith, N.A.: Improved part-of-speech tagging for online conversational text with word clusters. In: Proceedings of NAACL, pp. 380–390 (2013)Google Scholar
  18. 18.
    Ratnaparkhi, A.: A maximum entropy model for part-of-speech tagging. In: Proceedings of EMNLP, pp. 133–142 (1996)Google Scholar
  19. 19.
    Sha, F.P.: Shallow parsing with conditional random fields. In: Proceedings of NAACL, pp. 213–220 (2003)Google Scholar
  20. 20.
    Toutanova, K., Manning, C.: Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In: Proceedings of EMNLP, pp. 63–70 (2000)Google Scholar
  21. 21.
    Toutanova, K., Klein, D., Manning, C., Singer, Y.: Feature-rich part-of-speech tagging with a cyclic dependency network. In: Proceedings of NAACL, pp. 252–259 (2003)Google Scholar
  22. 22.
    Tran, T.O., Le, A.C., Ha, Q.T., Le, H.Q.: An experimental study on Vietnamese POS tagging. In: Proceedings of IALP, pp. 23–27 (2009)Google Scholar
  23. 23.
    Tran, T.O., Le, A.C., Ha, Q.T.: Improving Vietnamese word segmentation and POS tagging using MEM with various kinds of resources. J. Nat. Lang. Process. 17(3), 41–60 (2010)CrossRefGoogle Scholar
  24. 24.
    Vyas, Y., Gella, S.: POS tagging of English-Hindi code-mixed social media content. In: Proceedings of EMNLP, pp. 974–979 (2014)Google Scholar
  25. 25.
    Zheng, X., Chen, H., Xu, T.: Deep learning for Chinese word segmentation and POS tagging. In: Proceedings of EMNLP, pp. 647–657 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Ngo Xuan Bach
    • 1
    • 2
    Email author
  • Nguyen Dieu Linh
    • 1
  • Tu Minh Phuong
    • 1
    • 2
  1. 1.Department of Computer SciencePosts and Telecommunications Institute of TechnologyHanoiVietnam
  2. 2.FPT Software Research LabHanoiVietnam

Personalised recommendations