Chinese Named Entity Recognition with a Sequence Labeling Approach: Based on Characters, or Based on Words?

  • Zhangxun Liu
  • Conghui Zhu
  • Tiejun Zhao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6216)


Named Entity Recognition (NER), an important problem of Natural Language Processing, is the basis for other applications, such as Data Mining and Relation Extraction. With a sequence labeling approach, this paper wants to answer which kind of tokens that should be taken as the graininess in NER task, characters or words. Meanwhile, we use not only local context features within a sentence, but also global knowledge features extracting from other occurrences of each word in the whole corpus. The results show that without the global features the person names and the location names have good result based on characters, but the organization names are more suitable based on words. When global features are added, the performance of based on words improved significantly.


Chinese Named Entity Recognition CRF graininess 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: Proceedings of the 18th International Conference on Machine Learning (2001)Google Scholar
  2. 2.
    Chieu, H.L., Ng, H.T.: Named Entity Recognition: A Maximum Entropy Approach Using Global Information. In: Proceedings of the Nineteenth International Conference on Computational Linguistics, pp. 190–196 (2002)Google Scholar
  3. 3.
    Wu, Y., Zhao, J., Xu, B.: Chinese Named Entity Recognition Model Based on Multiple Features. In: Proceedings of HLT/EMNLP, Vancouver, B.C., Canada, October 6-8, pp. 427–434, (2005)Google Scholar
  4. 4.
    Chieu, H.L., Ng, H.T.: Named Entity Recognition with a Maximum Entropy Approach (2003)Google Scholar
  5. 5.
    Krupka, G.R., IsoQuest, K.H.: Description of the NerOwl Extractor System as Used for MUC-7. In: Proceedings of the 7th Message Understanding Conference, Virginia, pp. 21–28 (2005)Google Scholar
  6. 6.
    Thamar: Exploiting Named Entity Taggers in a Second Language. ACL (2007)Google Scholar
  7. 7.
    Babych, B., Hartley, A.: Improving machine translation quality with automatic named entity recognition. In: Proceedings of the EACL 2003 Workshop on MT and Other Language Technology Tools (2003)Google Scholar
  8. 8.
    Krishnan, V., Manning, C.D.: An Effective Two-Stage Model for Exploiting Non-Local Dependencies in Named Entity Recognition. ACL (2006)Google Scholar
  9. 9.
    Batchelor, C.R., Corbett, P.T.: Semantic enrichment of journal articles using chemical named entity recognition. ACL (2007)Google Scholar
  10. 10.
    Chinchor, N.: MUC-7 named entity task definition, version 3.5. In: Proceedings of the Seventh Message Understanding Conference (1998)Google Scholar
  11. 11.
    Sundheim, B.M.: Named entity task definition, version 2.1. In: Proceedings of the Sixth Message Understanding Conference, pp. 319–332 (1995)Google Scholar
  12. 12.
    Borthwick, A.: A Maximum Entropy Approach to Named Entity Recognition. Ph.D. thesis, Computer Science Department, New York University (1999)Google Scholar
  13. 13.
    Bikel, D.M., Schwartz, R., Weischedel, R.M.: An algorithm that learns what’s in a name. Machine Learning, 211–231 (1999)Google Scholar
  14. 14.
    Sundheim, B.M.: Named entity task definition, version 2.1. In: Proceedings of the Sixth Message Understanding Conference (1995)Google Scholar
  15. 15.
    Mihalcea, R., Moldovan, D.: Document indexing using named entities. Studies in Informatics and Control, vol. 10 (January 2001)Google Scholar
  16. 16.
    Mann, G.S.: Fine-grained proper noun ontologies for question answering. In: SemaNet 2002: Building and Using Semantic Networks, Taipei, Taiwan (2002)Google Scholar
  17. 17.
    Darroch, J., Ratcliff, D.: Generalized iterative scaling for log-linear models. Annals of Mathematical Statistics (1972)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Zhangxun Liu
    • 1
  • Conghui Zhu
    • 1
  • Tiejun Zhao
    • 1
  1. 1.Harbin Institute of TechnologyMOE-MS Key Laboratory of NLP and speechHarbinChina

Personalised recommendations