Advertisement

A Robust Geometric Model for Argument Classification

  • Cristina Giannone
  • Danilo Croce
  • Roberto Basili
  • Diego De Cao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5883)

Abstract

Argument classification is the task of assigning semantic roles to syntactic structures in natural language sentences. Supervised learning techniques for frame semantics have been recently shown to benefit from rich sets of syntactic features. However argument classification is also highly dependent on the semantics of the involved lexicals. Empirical studies have shown that domain dependence of lexical information causes large performance drops in outside domain tests. In this paper a distributional approach is proposed to improve the robustness of the learning model against out-of-domain lexical phenomena.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fillmore, C.J.: Frames and the semantics of understanding. Quaderni di Semantica 4(2), 222–254 (1985)Google Scholar
  2. 2.
    Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Computational Linguistics 28, 245–288 (2002)CrossRefGoogle Scholar
  3. 3.
    Shen, D., Lapata, M.: Using semantic roles to improve question answering. In: Proc. of EMNLP-CoNLL, Prague, pp. 12–21 (2007)Google Scholar
  4. 4.
    Punyakanok, V., Roth, D., Yih, W.: The necessity of syntactic parsing for s.antic role labeling. In: Proceedings of IJCAI 2005 (2005)Google Scholar
  5. 5.
    Johansson, R., Nugues, P.: Semantic structure extraction using nonprojective dependency trees. In: Proc. of SemEval 2007, Prague, June 23-24 (2007)Google Scholar
  6. 6.
    Moschitti, A., Pighin, D., Basili, R.: Tree kernels for semantic role labeling. Computational Linguistics 34(2), 193–224 (2008)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Johansson, R., Nugues, P.: The effect of syntactic representation on semantic role labeling. In: Proceedings of COLING, Manchester, UK, August 18-22 (2008)Google Scholar
  8. 8.
    Sahlgren, M.: The Word-Space Model. PhD thesis, Stockholm University (2006)Google Scholar
  9. 9.
    Padó, S., Lapata, M.: Dependency-based construction of semantic space models. Computational Linguistics 33(2), 161–199 (2007)CrossRefGoogle Scholar
  10. 10.
    Dowty, D.: Thematic proto-roles and argument selection. Language 6(3) (1991)Google Scholar
  11. 11.
    Pradhan, S.S., Ward, W., Martin, J.H.: Towards robust semantic role labeling. Computational Linguistics 34(2), 289–310 (2008)CrossRefGoogle Scholar
  12. 12.
    Baker, C.F., Ellsworth, M., Erk, K.: Semeval-2007 task 19: Frame s.antic structure extraction. In: Proc. of SemEval, Prague, pp. 99–104 (2007)Google Scholar
  13. 13.
    Fürstenau, H., Lapata, M.: Semi-supervised semantic role labeling. In: Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), Athens, Greece. Association for Computational Linguistics, March 2009, pp. 220–228 (2009)Google Scholar
  14. 14.
    Erk, K.: A simple, similarity-based model for selectional preferences. In: Proc. of the 45th Annual Meeting of the Association of Computational Linguistics, Prague. Association for Computational Linguistics, June 2007, pp. 216–223 (2007)Google Scholar
  15. 15.
    Pennacchiotti, M., De Cao, D., Basili, R., Croce, D., Roth, M.: Automatic induction of framenet lexical units. In: Proc. of EMNLP 2008 Hawaii (2008)Google Scholar
  16. 16.
    Schütze, H.: Automatic word sense discrimination. Computational Linguistics 24(1), 97–124 (1998)Google Scholar
  17. 17.
    Harris, Z.: Distributional structure. In: Katz, J.J., Fodor, J.A. (eds.) The Philosophy of Linguistics. Oxford University Press, New York (1964)Google Scholar
  18. 18.
    Pado, S.: Cross-Lingual Annotation Projection Models for Role-Semantic Information. PhD thesis, Saarland University (2007)Google Scholar
  19. 19.
    Landauer, T., Dumais, S.: A solution to plato’s probl.: The latent semantic analysis theory of acquisition, induction and representation of knowledge. Psychological Review 104, 211–240 (1997)CrossRefGoogle Scholar
  20. 20.
    Heyer, L.J., Kruglyak, S., Yooseph, S.: Exploring expression data: Identification and analysis of coexpressed genes. Genome Research (9), 1106–1115 (1999)Google Scholar
  21. 21.
    Basili, R., De Cao, D., Marocco, P., Pennacchiotti, M.: Learning selectional preferences for entailment or paraphrasing rules. In: Proc. of RANLP 2007 (2007)Google Scholar
  22. 22.
    Kuhn, H.W.: The hungarian method for the assignment probl. Naval Research Logistics Quarterly 2, 83–97 (1955)CrossRefMathSciNetGoogle Scholar
  23. 23.
    Finkel, J.R., Grenager, T., Manning, C.D.: Incorporating non-local information into information extraction systems by gibbs sampling. In: ACL. The Association for Computer Linguistics (2005)Google Scholar
  24. 24.
    Pado, S., Lapata, M.: Dependency-based construction of semantic space models. Computational Linguistics 33 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Cristina Giannone
    • 1
  • Danilo Croce
    • 1
  • Roberto Basili
    • 1
  • Diego De Cao
    • 1
  1. 1.University of Roma Tor VergataRomaItaly

Personalised recommendations