Latent Topic Models of Surface Syntactic Information

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

Abstract

Topic Models like Latent Dirichlet Allocation have been widely used for their robustness in estimating text models through mixtures of latent topics. Although LDA has been mostly used as a strictly lexicalized approach, it can be effectively applicable to a much richer set of linguistic structures. A novel application of LDA is here presented that acquires suitable grammatical generalizations for semantic tasks tightly dependent on NL syntax. We show how the resulting topics represent suitable generalizations over syntactic structures and lexical information as well. The evaluation on two different classification tasks, such as predicate recognition and question classification, shows that state of the art results are obtained.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baker, C., Ellsworth, M., Erk, K.: Semeval-2007 task 19: Frame semantic structure extraction. In: Proc. of SemEval 2007, Czech Republic, pp. 99–104 (2007)Google Scholar
  2. 2.
    Baker, C.F., Fillmore, C.J., Lowe, J.B.: The berkeley framenet project (1998)Google Scholar
  3. 3.
    Blei, D., McAuliffe, J.: Supervised topic models. In: Proceedings of Advances in Neural Information Processing Systems (2007)Google Scholar
  4. 4.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. Journal of Machine Learning Research 3(4-5), 993–1022 (2003)MATHGoogle Scholar
  5. 5.
    Boyd-Graber, J., Blei, D.: Syntactic topic models. In: Proceedings of Advances in Neural Information Processing Systems (2008)Google Scholar
  6. 6.
    Boyd-Graber, J., Blei, D., Zhu, X.: A topic model for word sense disambiguation. In: Proc.of the Joint Conference on EMNLP and CoNLL, pp. 1024–1033 (2007)Google Scholar
  7. 7.
    Brody, S., Lapata, M.: Bayesian word sense induction. In: Proceedings of the Conference of the European Chapter of the ACL, pp. 103–111 (2009)Google Scholar
  8. 8.
    Collins, M., Duffy, N.: New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In: ACL 2002 (2002)Google Scholar
  9. 9.
    Nello, C., John, S.-T., Huma, L.: Latent semantic kernels. J. Intell. Inf. Syst. 18(2-3), 127–152 (2002)Google Scholar
  10. 10.
    Erk, K., Pado, S.: Shalmaneser - a flexible toolbox for semantic role assignment. In: Proceedings of LREC 2006, Genoa, Italy (2006)Google Scholar
  11. 11.
    Fillmore, C.J.: Frames and the semantics of understanding. Quaderni di semantica 6(2), 222–254 (1985)Google Scholar
  12. 12.
    Gildea, D., Jurafsky, D.: Automatic Labeling of Semantic Roles. Computational Linguistics 28(3), 245–288 (2002)CrossRefGoogle Scholar
  13. 13.
    Griffiths, T., Steyvers, M., Blei, D., Tenenbaum, J.: Integrating topics and syntax. In: Proceedings of NIPS 2005, pp. 537–544 (2005)Google Scholar
  14. 14.
    Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proceedings of the National Academy of Sciences, 5228–5235 (2004)Google Scholar
  15. 15.
    Johansson, R., Nugues, P.: Semantic structure extraction using nonprojective dependency trees. In: Proceedings of SemEval 2007, Czech Republic (2007)Google Scholar
  16. 16.
    Kwok, C.C.T., Etzioni, O., Weld, D.S.: Scaling question answering to the web. In: WWW, pp. 150–161 (2001)Google Scholar
  17. 17.
    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
  18. 18.
    Li, X., Roth, D.: Learning question classifiers. In: Proceedings of ACL 2002 (2002)Google Scholar
  19. 19.
    Li, X., Roth, D.: Learning question classifiers: the role of semantic information. Nat. Lang. Eng. 12(3), 229–249 (2006)CrossRefGoogle Scholar
  20. 20.
    Minka, T., Lafferty, J.: Expectation-propagation for the generative aspect model. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence, pp. 352–359 (2002)Google Scholar
  21. 21.
    Moschitti, A.: Efficient convolution kernels for dependency and constituent syntactic trees. In: ECML, Berlin, Germany, pp. 318–329 (2006); Machine LearningGoogle Scholar
  22. 22.
    Moschitti, A., Pighin, D., Basili, R.: Tree Kernels for Semantic Role Labeling. Computational Linguistics Special Issue on Semantic Role Labeling (3), 245–288 (2008)Google Scholar
  23. 23.
    Moschitti, A., Quarteroni, S., Basili, R., Manandhar, S.: Exploiting syntactic and shallow semantic kernels for question answer classification. In: Proceedings of ACL 2007 (2007)Google Scholar
  24. 24.
    Pradhan, S., Hacioglu, K., Krugler, V., Ward, W., Martin, J.H., Jurafsky, D.: Support Vector Learning for Semantic Argument Classification. Machine Learning 60(1-3), 11–39 (2005)CrossRefGoogle Scholar
  25. 25.
    Rosen-Zvi, M., Griffiths, T., Steyvers, M., Smyth, P.: The author-topic model for authors and documents. In: Proceedings of Uncertainty in Artificial Intelligence, pp. 487–494 (2004)Google Scholar
  26. 26.
    Tomás, D., Giuliano, C.: A semi-supervised approach to question classification. In: Proc. of the 17th European Symposium on Artificial Neural Networks, Bruges, Belgium (2009)Google Scholar
  27. 27.
    Toutanova, K., Johnson, M.: A bayesian lda-based model for semi-supervised part-of-speech tagging. In: Proceedings of Advances in Neural Information Processing Systems (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Roberto Basili
    • 1
  • C. Giannone
    • 1
  • Danilo Croce
    • 1
  • C. Domeniconi
    • 2
  1. 1.Dept. of Enterprise EngineeringUniversity of Roma Tor VergataRomaItaly
  2. 2.Dept. of Computer ScienceGeorge Mason UniversityUSA

Personalised recommendations