Structured Learning for Semantic Role Labeling

  • Danilo Croce
  • Roberto Basili
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6934)


The use of complex grammatical features in statistical language learning assumes the availability of large scale training data and good quality parsers, especially for language different from English. In this paper, we show how good quality FrameNet SRL systems can be obtained, without relying on full syntactic parsing, by backing off to surface grammatical representations and structured learning. This model is here shown to achieve state-of-art results in standard benchmarks, while its robustness is confirmed in poor training conditions, for a language different for English, i.e. Italian.


Noun Phrase Latent Semantic Analysis Parse Tree Boundary Detection Semantic Role 
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.
    Altun, Y., Tsochantaridis, I., Hofmann, T.: Hidden Markov support vector machines. In: Proceedings of the International Conference on Machine Learning (2003)Google Scholar
  2. 2.
    Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The wacky wide web: a collection of very large linguistically processed web-crawled corpora. Language Resources and Evaluation 43(3), 209–226 (2009)CrossRefGoogle Scholar
  3. 3.
    Collins, M.: Three generative, lexicalised models for statistical parsing. In: Proceedings of ACL 1997, pp. 16–23 (1997)Google Scholar
  4. 4.
    Collins, M., Duffy, N.: Convolution kernels for natural language. In: Proceedings of Neural Information Processing Systems (NIPS), pp. 625–632 (2001)Google Scholar
  5. 5.
    Croce, D., Giannone, C., Annesi, P., Basili, R.: Towards open-domain semantic role labeling. In: ACL, pp. 237–246 (2010)Google Scholar
  6. 6.
    Gildea, D., Jurafsky, D.: Automatic Labeling of Semantic Roles. Computational Linguistics 28(3), 245–288 (2002)CrossRefGoogle Scholar
  7. 7.
    Golub, G., Kahan, W.: Calculating the singular values and pseudo-inverse of a matrix. Journal of the Society for Industrial and Applied Mathematics 2(2) (1965)Google Scholar
  8. 8.
    Harris, Z.: Distributional structure. In: Katz, J.J., Fodor, J.A. (eds.) The Philosophy of Linguistics. Oxford University Press, Oxford (1964)Google Scholar
  9. 9.
    Huang, F., Yates, A.: Distributional representations for handling sparsity in supervised sequence-labeling. In: ACL-IJCNLP 2009, vol. 1, pp. 495–503. ACL, Morristown (2009)Google Scholar
  10. 10.
    Johansson, R., Nugues, P.: Dependency-based syntactic-semantic analysis with propbank and nombank. In: Proceedings of CoNLL 2008, Manchester, UK, August 16-17 (2008)Google Scholar
  11. 11.
    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
  12. 12.
    Landauer, T., Dumais, S.: A solution to plato’s problem: The latent semantic analysis theory of acquisition, induction and representation of knowledge. Psychological Review 104(2), 211–240 (1997)CrossRefGoogle Scholar
  13. 13.
    Lin, D.: Automatic retrieval and clustering of similar word. In: Proceedings of COLING-ACL, Montreal, Canada (1998)Google Scholar
  14. 14.
    Màrquez, L., Comas, P., Gimènez, J., Català, N.: Semantic role labeling as sequential tagging. In: Proceedings of CoNLL-2005 Shared Task (2005)Google Scholar
  15. 15.
    Moschitti, A.: Efficient convolution kernels for dependency and constituent syntactic trees. In: ECML, Berlin, Germany, pp. 318–329 (2006); Machine LearningGoogle Scholar
  16. 16.
    Moschitti, A., Pighin, D., Basili, R.: Tree kernels for semantic role labeling. Computational Linguistics 34 (2008)Google Scholar
  17. 17.
    Moschitti, A., Quarteroni, S., Basili, R., Manandhar, S.: Exploiting syntactic and shallow semantic kernels for question answer classification. In: Proc. of ACL 2007, pp. 776–783 (2007)Google Scholar
  18. 18.
    Pado, S., Lapata, M.: Dependency-based construction of semantic space models. Computational Linguistics 33(2) (2007)Google Scholar
  19. 19.
    Pradhan, S., Hacioglu, K., Krugler, V., Ward, W., Martin, J.H., Jurafsky, D.: Support vector learning for semantic argument classification. Machine Learning Journal (2005)Google Scholar
  20. 20.
    Pradhan, S.S., Ward, W., Martin, J.H.: Towards robust semantic role labeling. Comput. Linguist. 34(2), 289–310 (2008)CrossRefGoogle Scholar
  21. 21.
    Sahlgren, M.: The Word-Space Model. Ph.D. thesis, Stockholm University (2006)Google Scholar
  22. 22.
    Schutze, H.: Automatic word sense discrimination. Journal of Computational Linguistics 24, 97–123 (1998)Google Scholar
  23. 23.
    Steedman, M.: The syntactic process. MIT Press, Cambridge (2000)zbMATHGoogle Scholar
  24. 24.
    Tonelli, S., Pianta, E.: Frame information transfer from english to italian. In: LREC 2008 (2008)Google Scholar
  25. 25.
    Toutanova, K., Haghighi, A., Manning, C.D.: A global joint model for semantic role labeling. Comput. Linguist. 34(2), 161–191 (2008)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Machine Learning Reserach 6 (December 2005)Google Scholar
  27. 27.
    Turney, P.D., Pantel, P.: From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research 37, 141–188 (2010)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Danilo Croce
    • 1
  • Roberto Basili
    • 1
  1. 1.Department of Enterprise EngineeringUniversity of Roma, Tor VergataRomaItaly

Personalised recommendations