Domain Adaptation by Active Learning

  • Giuseppe Attardi
  • Maria Simi
  • Andrea Zanelli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7689)


We tackled the Evalita 2011 Domain Adaptation task with a strategy of active learning. The DeSR parser can be configured to provide different measures of perplexity in its own ability to parse sentences correctly. After parsing sentences in the target domain, a small number of the sentences with the highest perplexity were selected, revised manually and added to the training corpus in order to build a new parser model incorporating some knowledge from the target domain. The process was repeated a few times for building a new training resource partially adapted to the target domain. Using the new resource we trained three stacked parsers, and their combination was used to produce the final results.


Dependency parser domain adaptation active learning stacked parser parser combination 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Atserias, J., Attardi, G., Simi, M., Zaragoza, H.: Active Learning for Building a Corpus of Questions for Parsing. In: Proceedings of LREC 2010, Malta (2010)Google Scholar
  2. 2.
    Attardi, G.: Experiments with a Multilanguage Non-Projective Dependency Parser. In: Proc. of the Tenth Conference on Natural Language Learning, New York (2006)Google Scholar
  3. 3.
    Attardi, G., Dell’Orletta, F., Simi, M., Turian, J.: Accurate Dependency Parsing with a Stacked Multilayer Perceptron. In: Proc. of Workshop Evalita 2009 (2009) ISBN 978-88-903581-1-1Google Scholar
  4. 4.
    Attardi, G., Dell’Orletta, F.: Reverse Revision and Linear Tree Combination for Dependency Parsing. In: Proceedings of NAACL HLT 2009 (2009)Google Scholar
  5. 5.
    Attardi, G., Simi, M., Zanelli, A.: Tuning DeSR for Dependency Parsing of Italian. In: Working Notes of EVALITA 2011, Rome, Italy, January 24-25 (2012) ISSN 2240-5186Google Scholar
  6. 6.
    Charniak, E.: Statistical parsing with a context-free grammar and word statistics. In: Proc. AAAI, pp. 598–603 (1997)Google Scholar
  7. 7.
    Dell’Orletta, F., Marchi, S., Montemagni, S., Venturi, G., Agnoloni, T., Francesconi, T.: Domain Adaptation for Dependency Parsing at Evalita 2011. In: Working Notes of EVALITA 2011, Rome, Italy, January 24-25 (2012) ISSN 2240-5186Google Scholar
  8. 8.
    McClosky, D., Charniak, E., Johnson, M.: Automatic Domain Adaptation for Parsing. In: Proc. of NAACL – HLT 2010 Conference, Los Angeles, CA (2010)Google Scholar
  9. 9.
    Nivre, J., Scholz, M.: Deterministic Dependency Parsing of English Text. In: Proc. of COLING 2004, Geneva, Switzerland, pp. 64–70 (2004)Google Scholar
  10. 10.
    Steedman, M., et al.: CLSP WS-02 Final Report: Semi-Supervised Training for Statistical Parsing. Technical Report, Johns Hopkins University (2003)Google Scholar
  11. 11.
    Yamada, H., Matsumoto, Y.: Statistical Dependency Analysis with Support Vector Machines. In: Proc. of the 8th International Workshop on Parsing Technologies (IWPT), pp. 195–206 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Giuseppe Attardi
    • 1
  • Maria Simi
    • 1
  • Andrea Zanelli
    • 1
  1. 1.Dipartimento di InformaticaUniversità di PisaPisaItaly

Personalised recommendations