Applying Conditional Random Fields to Chinese Shallow Parsing

  • Yongmei Tan
  • Tianshun Yao
  • Qing Chen
  • Jingbo Zhu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3406)


Chinese shallow parsing is a difficult, important and widely-studied sequence modeling problem. CRFs are new discriminative sequential models which may incorporate many rich features. This paper shows how conditional random fields (CRFs) can be efficiently applied to Chinese shallow parsing. We employ using CRFs and HMMs on a same data set. Our results confirm that CRFs improve the performance upon HMMs. Our approach yields the F1 score of 90.38% in Chinese shallow parsing with the UPenn Chinese Treebank. CRFs have shown to perform well for Chinese shallow parsing due to their ability to capture arbitrary, overlapping features of the input in a Markov model.


Conditional Random Field Parse Tree Observation Sequence Label Sequence Syntactic Parsing 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, S., Liu, Q., Yang, Z.: Chunk Parsing with Maximym Entropy Principle. Chinese Journal of Computers 26(12), 1734–1738 (2003)MathSciNetGoogle Scholar
  2. 2.
    Zhang, Y., Zhou, Q.: Automatic identification of Chinese base phrases. Journal of Chinese Information Processing 16(16) (2002)Google Scholar
  3. 3.
    Zhou, Q., Sun, M., Huang, C.: Chunking parsing scheme for Chinese sentences. Chinese J. Computers 22(1), 1158–1165 (1999)Google Scholar
  4. 4.
    Zhao, J., Huang, C.: A transformation-based model for Chinese basenp recognition. Journal of Chinese Information Processing 13(2), 1–7 (1998)Google Scholar
  5. 5.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: Proc. 18th International Conf. on Machine Learning (2001)Google Scholar
  6. 6.
    Sha, F., Pereira, F.: Shallow Parsing with Conditional Random Fields. In: Proceedings of Human Language Technology-NAACL, Edmonton, Canada (2003)Google Scholar
  7. 7.
    McCallum, A., Feng, F.-f.: Chinese Word Segmentation with Conditional Random Fields and Integrated Domain Knowledge (2003)Google Scholar
  8. 8.
    McCallum, A., Li, W.: Early results for named entity recognition with conditional random fields, Feature Induction and Web-Enhanced Lexicons. In: Proceedings of Seventh Conference on Natural Language Learning, CoNLL (2003)Google Scholar
  9. 9.
    Pinto, D., McCallum, A., Wei, X., Croft, W.B.: Table extraction using conditional random fields. In: Proc. of SIGIR, pp. 235–242 (2003)Google Scholar
  10. 10.
    Peng, F., McCallum, A.: Accurate information extraction from research papers. In: Proc. of HLT/NAACL (2004)Google Scholar
  11. 11.
    Ramashaw, L.A., Marcus, M.P.: Text chunking using transformation-based learning. In: Proceedings of the Third ACL Workshop on Very Large CorporaGoogle Scholar
  12. 12.
    Abney, S.: Parsing by chunks. In: Berwick, R.C., Abney, S.P., Tenny, C. (eds.) Principle-Based Parsing: Computation and Psycholinguistics, pp. 257–278. Kluwer Academic Publishers, Boston (1991)Google Scholar
  13. 13.
    Paz, A.: Introduction to probabilistic automata. Academic Press, London (1971)MATHGoogle Scholar
  14. 14.
    Bottou, L.: Une approche theorique del’apprentissage connexionniste: Applications a la reconnaissance de la parole, Doctoral dissertation, Universite de Paris XI (1991)Google Scholar
  15. 15.
    Ratnaparkhi, A.: A maximum entropy model for part-of-speech tagging. In: Proc. EMNLP. Association for Computational Linguistics, New Brunswick (1996)Google Scholar
  16. 16.
    Punyakanok, V.: The use of classifiers in sequential inference. NIPS 13 (2001)Google Scholar
  17. 17.
    Wallach, H.: Efficient Training of Conditional Random Fields, Thesis. Master of Science School of Cognitive Science, Division of Informatics. University of Edinburgh (2002)Google Scholar
  18. 18.
    McCallum, A., Freitag, D., Pereira, F.: Maximum entropy Markov models for information extraction and segmentation. In: Proc. ICML 2000, Stanford, California, pp. 591–598 (2000)Google Scholar
  19. 19.
    McCallum, A.K.: MALLET: A Machine Learning for Language Toolkit. (2002),
  20. 20.
    Yao, T., et al.: Natural Language Processing – A research of making computers understand human languages. Tsinghua University Press, Beijing (2002) (in Chinese)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Yongmei Tan
    • 1
  • Tianshun Yao
    • 1
  • Qing Chen
    • 1
  • Jingbo Zhu
    • 1
  1. 1.Natural Language Processing LabNortheastern UniversityShenyang

Personalised recommendations