Combining Czech Dependency Parsers

  • Tomáš Holan
  • Zdeněk Žabokrtský
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)


In this paper we describe in detail two dependency parsing techniques developed and evaluated using the Prague Dependency Treebank 2.0. Then we propose two approaches for combining various existing parsers in order to obtain better accuracy. The highest parsing accuracy reported in this paper is 85.84 %, which represents 1.86 % improvement compared to the best single state-of-the-art parser. To our knowledge, no better result achieved on the same data has been published yet.


Reduction Rule Punctuation Mark Dependency Parser Relative Error Reduction Individual Parser 
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.
    Zeman, D.: Parsing with a Statistical Dependency. PhD thesis, Charles University, MFF (2004)Google Scholar
  2. 2.
    Zeman, D., Žabokrtský, Z.: Improving Parsing Accuracy by Combining Diverse Dependency Parsers. In: Proceedings of the 9th International Workshop on Parsing Technologies, Vancouver, BC, Canada (2005)Google Scholar
  3. 3.
    Holan, T.: Tvorba závislostního syntaktického analyzátoru. In: Sborník semináře MIS 2004, Matfyzpress, Prague, Czech Republic (2004)Google Scholar
  4. 4.
    Nivre, J., Nilsson, J.: Pseudo-Projective Dependency Parsing. In: Proceedings of ACL 2005, Ann Arbor, Michigan (2005)Google Scholar
  5. 5.
    Holan, T.: Genetické učení závislostních analyzátorů. In: Sborník semináře ITAT 2005, UPJŠ, Košice (2005)Google Scholar
  6. 6.
    McDonald, R., Pereira, F., Ribarov, K., Hajič, J.: Non-Projective Dependency Parsing using Spanning Tree Algorithms. In: Proceedings of HTL/EMNLP 2005, Vancouver, BC, Canada (2005)Google Scholar
  7. 7.
    Hajič, J., Collins, M., Ramshaw, L., Tillmann, C.: A Statistical Parser for Czech. In: Proceedings ACL 1999, Maryland, USA (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tomáš Holan
    • 1
  • Zdeněk Žabokrtský
    • 1
  1. 1.Faculty of Mathematics and PhysicsCharles UniversityPragueCzech Republic

Personalised recommendations