Advertisement

UNIPI Participation in the Evalita 2011 Anaphora Resolution Task

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

Abstract

The Anaphora Resolution task of Evalita 2011 was intended to measure the ability of participating systems to recognize mentions of the same real-world entity within a given document. The UNIPI system is based on the analysis of dependency parse trees and on similarity clustering. Mention detection relies on parse trees obtained by re-parsing texts with DeSR, and on ad-hoc heuristics to deal with specific cases, when mentions boundaries do not correspond to sub-trees. A binary classifier, based on Maximum Entropy, is used to decide whether there is a coreference relationship between each pair of mentions detected in the previous phase. Clustering of entities is performed by a greedy clustering algorithm.

Keywords

Anaphora resolution maximum entropy similarity clustering parse analysis mention detection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Attardi, G., et al.: Tanl (Text Analytics and Natural Language Processing). SemaWiki project (2009), http://medialab.di.unipi.it/wiki/SemaWiki
  2. 2.
    Attardi, G., Dei Rossi, S., Dell’Orletta, F., Vecchi, E.M.: The Tanl Named Entity Recognizer at Evalita 2009. In: Evalita 2009, Reggio Emilia (2009)Google Scholar
  3. 3.
    Attardi, G., Dei Rossi, S., Simi, M.: TANL-1: Coreference Resolution by Parse Analysis and Similarity Clustering. In: Proc. of SemEval 2010, Uppsala (2010)Google Scholar
  4. 4.
    Le, Z.: Maximum Entropy Modeling Toolkit for Python and C++, Reference ManualGoogle Scholar
  5. 5.
    Lee, H., Peirsman, Y., Chang, A., Chambers, N., Surdeanu, M., Jurafsky, D.: Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task. In: Proceedings of the 15th Conference on Computational Natural Language Learning: Shared Task, Portland, Oregon, June 23-24, pp. 28–34 (2011)Google Scholar
  6. 6.
    Luo, X., Ittycheriah, A., Jing, H., Kambhatla, N., Roukos, S.: A Mention-Synchronous Coreference Resolution Algorithm Based on the Bell Tree. In: Proceedings of the ACL 2004, Barcelona (2004)Google Scholar
  7. 7.
    Ng, V.: Machine Learning for Coreference Resolution: From Local Classification to Global Ranking. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), Ann Arbor, MI, pp. 157–164 (2005)Google Scholar
  8. 8.
    Pradhan, S., Ramshaw, L., Marcus, M., Palmer, M., Weischedel, R., Xue, N.: Conll-2011 shared task: Modeling unrestricted coreference in OntoNotes. In: Proceedings of the Fifteenth Conference on Computational Natural Language Learning (CoNLL 2011), Portland, Oregon (2011)Google Scholar
  9. 9.
    Rand, W.M.: Objective criteria for the evaluation of clustering methods. Journal od the American Statistical Association 66(336) (1971)Google Scholar
  10. 10.
    Recasens, M., Màrquez, L., Sapena, E., Martí, M.A., Taulé, M., Hoste, V., Poesio, M., Versley, Y.: Semeval-2010 task 1: Coreference resolution in multiple languages. In: Proceedings of SEMEVAL 2010, Uppsala (2010)Google Scholar
  11. 11.
    Soon, W.M., Ng, H.T., Lim, D.C.Y.: Coreference Resolution of Noun Phrases. Computational Linguistics 27(4), 521–544 (2001)CrossRefGoogle Scholar
  12. 12.
    Uryupina, O., Poesio, M.: Evalita 2011: Anaphora Resolution Task. In: Working Notes of Evalita 2011, Rome, Italy, January 24-25 (2012) ISSN 2240-5186Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Giuseppe Attardi
    • 1
  • Stefano Dei Rossi
    • 1
  • Maria Simi
    • 1
  1. 1.Dipartimento di InformaticaUniversità di PisaPisaItaly

Personalised recommendations