Syntactic Tree Kernels for Event-Time Temporal Relation Learning

  • Seyed Abolghasem Mirroshandel
  • Mahdy Khayyamian
  • Gholamreza Ghassem-Sani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6562)


Temporal relation classification is one of the contemporary demanding tasks in natural language processing. This task can be used in various applications such as question answering, summarization, and language specific information retrieval. In this paper, we propose an improved algorithm for classifying temporal relations between events and times, using support vector machines (SVM). Along with gold-standard corpus features, the proposed method aims at exploiting useful syntactic features, which are automatically generated, to improve accuracy of the classification. Accordingly, a number of novel kernel functions are introduced and evaluated for temporal relation classification. The result of experiments clearly shows that adding syntactic features results in a notable performance improvement over the state of the art method, which merely employs gold-standard features.


Temporal Relations between Event and Time Information Retrieval Text Mining Classification 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mani, I., Marc, V., Wellner, B., Lee, C.M., Pustejovsky, J.: Machine Learning of Temporal Relations. In: ACL, vol. 44, pp. 753–760 (2006)Google Scholar
  2. 2.
    Tatu, M., Srikanth, M.: Experiments with Reasoning for Temporal Relations between Events. In: Coling 2008, pp. 857–864 (2008)Google Scholar
  3. 3.
    Khayyamian, M., Mirroshandel, S.A., Abolhassani, H.: Syntactic Tree-based Relation Extraction Using a Generalization of Collins and Duffy Convolution Tree Kernel. In: HLT/NAACL 2009, pp. 66–71 (2009)Google Scholar
  4. 4.
    Chklovski, T., Pantel, P.: Global path-based refinement of noisy graphs applied to verb semantics. In: Dale, R., Wong, K.-F., Su, J., Kwong, O.Y. (eds.) IJCNLP 2005. LNCS (LNAI), vol. 3651, pp. 792–803. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Abe, S., Inui, K., Matsumoto, Y.: Two-Phased Event Relation Acquisition Coupling the Relation-Oriented and Argument-Oriented Approaches. In: Coling 2008, pp. 1–8 (2008)Google Scholar
  6. 6.
    Chambers, N., Wang, S., Jurafsky, D.: Classifying Temporal Relations between Events. In: ACL, vol. 45, pp. 173–176 (2007) Google Scholar
  7. 7.
    Lapata, M., Lascarides, A.: Learning Sentence-Internal Temporal Relations. Journal of Artificial Intelligence Research 27, 85–117 (2006)zbMATHGoogle Scholar
  8. 8.
    Allen, J.F.: Towards a General Theory of Action and Time. Artificial Intelligence 23, 123–154 (1984)CrossRefzbMATHGoogle Scholar
  9. 9.
    Harris, Z.: Mathematical Structure of Language. John Wiley Sons, New York (1968)zbMATHGoogle Scholar
  10. 10.
    Lin, D., Pantel, P.: Dirt - Discovery of Inference Rules From Text. In: The 7th ACM SIGKDD, pp. 323–328 (2001)Google Scholar
  11. 11.
    Szpektor, I., Tanev, H., Dagan, I.: Scaling Web-based Acquisition of Entailment Relations. In: EMNLP 2004, pp. 41–48 (2004)Google Scholar
  12. 12.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A Training Algorithm for Optimal Margin Classifiers. In: COLT 1992, pp. 144–152. ACM, New York (1992)Google Scholar
  13. 13.
    Cortes, C., Vapnik, V.: Support-Vector Networks. Machine Learning, 273–297 (1995)Google Scholar
  14. 14.
    Collins, M., Duffy, N.: Convolution Kernels for Natural Language. In: Advances in Neural Information Processing Systems, vol. 14, pp. 625–632. MIT Press, Cambridge (2001)Google Scholar
  15. 15.
    Zhang, M., Zhang, J., Su, J., Zhou, G.D.: A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features. In: ACL, vol. 44, pp. 825–832 (2006)Google Scholar
  16. 16.
    Pustejovsky, J., Hanks, P., Sauri, R., See, A., Gaizauskas, R., Setzer, A., Radev, D., Sundheim, B., Day, D., Ferro, L., Lazo, M.: The TIMEBANK Corpus. In: Corpus Linguistics 2003, pp. 647–656 (2003)Google Scholar
  17. 17.
    Mani, I., Wellner, B., Verhagen, M., Pustejovsky, J.: Three Approaches to Learning Tlinks in TimeML. In Technical Report CS-07-268. Brandeis University, Waltham, USA (2007)Google Scholar
  18. 18.
    Chang, C. C., Lin, C.J.: Libsvm: a Library For Support Vector Machines (2001), software available at
  19. 19.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Seyed Abolghasem Mirroshandel
    • 1
  • Mahdy Khayyamian
    • 1
  • Gholamreza Ghassem-Sani
    • 1
  1. 1.Department of Computer EngineeringSharif University of TechnologyTehranIran

Personalised recommendations