On the Identification of Temporal Clauses

  • Georgiana Puşcaşu
  • Patricio Martínez Barco
  • Estela Saquete Boró
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4293)


This paper describes a machine learning approach to the identification of temporal clauses by disambiguating the subordinating conjunctions used to introduce them. Temporal clauses are regularly marked by subordinators, many of which are ambiguous, being able to introduce clauses of different semantic roles. The paper also describes our work on generating an annotated corpus of sentences embedding clauses introduced by ambiguous subordinators that might have temporal value. Each such clause is annotated as temporal or non-temporal by testing whether it answers the questions when, how often or how long with respect to the action of its superordinate clause. Using this corpus, we then train and evaluate personalised classifiers for each ambiguous subordinator, in order to set apart temporal usages. Several classifiers are evaluated, and the best performing ones achieve an average accuracy of 89.23% across the set of ambiguous connectives.


Semantic Role Question Answering Main Clause Matrix Clause Subordinate Clause 
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.
    Daelemans, W., Zavrel, J., Sloot, K., Bosch, A.: TiMBL Tilburg Memory Based Learner, version 51. Ilk technical report 04–02 (2004)Google Scholar
  2. 2.
    Davidson, D.: The Logical Form of Action Sentences. University of Pittsburgh Press (1967)Google Scholar
  3. 3.
    Filatova, E., Hovy, E.: Assigning Time-Stamps to Event-Clauses. In: Proceedings of the 2001 ACL Workshop on Temporal and Spatial Information Processing (2001)Google Scholar
  4. 4.
    Grosz, B., Sidner, C.: Attentions, Intentions, and the Structure of Discourse. In: Computational Linguistics (1986)Google Scholar
  5. 5.
    Haiman, J., Thompson, S.: Clause Combining in Grammar and Discourse. John Benjamins, Amsterdam (1988)Google Scholar
  6. 6.
    Hirschberg, J., Litman, D.: Empirical Studies on the Disambiguation of Cue Phrases. In: Computational Linguistics (1993)Google Scholar
  7. 7.
    Hutchinson, B.: Automatic Classification of Discourse Markers by their Cooccurrences. In: Proceedings of ESSLLI 2003 Workshop on The Meaning and Implementation of Discourse Particles (2003)Google Scholar
  8. 8.
    Hutchinson, B.: Acquiring the Meaning of Discourse Markers. In: Proceedings of ACL 2004 (2004)Google Scholar
  9. 9.
    Lapata, M., Lascarides, A.: Inferring Sentence-Internal Temporal Relations. In: Proceedings of HLT-NAACL 2004 (2004)Google Scholar
  10. 10.
    Lascarides, A., Oberlander, J.: Temporal Connectives in a Discourse Context. In: Proceedings of the European Chapter of the Association for Computational Linguistics (1993)Google Scholar
  11. 11.
    Mani, I., Shiffman, B.: Temporally Anchoring and Ordering Events in News. In: Pustejovsky, J., Gaizauskas, R. (eds.) Time and Event Recognition in Natural Language, John Benjamins, Amsterdam (2004)Google Scholar
  12. 12.
    Mani, I., Wilson, G.: Robust temporal processing of news. In: Proceedings of ACL 2000 (2000)Google Scholar
  13. 13.
    Moens, M., Steedman, M.: Temporal Ontology and Temporal Reference. In: Computational Linguistics (1988)Google Scholar
  14. 14.
    Polanyi, L.: A Formal Model of the Structure of Discourse. Journal of Pragmatics (1988)Google Scholar
  15. 15.
    Puscasu, G.: A Framework for Temporal Resolution. In: Proceedings of the LREC 2004 (2004)Google Scholar
  16. 16.
    Puscasu, G.: A Multilingual Method for Clause Splitting. In: Proceedings of the 7th Annual Colloquium for the UK Special Interest Group for Computational Linguistics (2004)Google Scholar
  17. 17.
    Pustejovsky, J., Sauri, R., Setzer, A., Gaizauskas, R., Ingria, R.: TimeML Annotation Guidelines Version 1.0 (2002), http://www.cs.brandeis.edu/~jamesp/arda/time/
  18. 18.
    Quirk, R., Greenbaum, S., Leech, G., Svartvik, J.: A Comprehensive Grammar of the English Language. Longman (1985)Google Scholar
  19. 19.
    Corpus, R.: English language, vol. 1 (2000), http://about.reuters.com/
  20. 20.
    Sampson, G.: English for the computer: the SUSANNE corpus and analytic scheme. Oxford University Press, Oxford (1995)Google Scholar
  21. 21.
    Schilder, F., Habel, C.: From Temporal Expressions to Temporal Information: Semantic Tagging of News Messages. In: Proceedings of the 2001 ACL Workshop on Temporal and Spatial Information Processing (2001)Google Scholar
  22. 22.
    Setzer, A.: Temporal Information in Newswire Articles: An Annotation Scheme and Corpus Study. PhD thesis, University of Sheffield (2001)Google Scholar
  23. 23.
    Setzer, A., Gaizauskas, R.: On the Importance of Annotating Event-Event Temporal Relations in Text. In: Proceedings of the LREC Workshop on Temporal Annotation Standards (2002)Google Scholar
  24. 24.
    Tapanainen, P., Jaervinen, T.: A non–projective dependency parser. In: Proceedings of the 5th Conference of Applied Natural Language Processing, ACL (1997)Google Scholar
  25. 25.
    Webber, B.: Tense as Discourse Anaphor. Computational Linguistics 14(2), 61–73 (1988)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Georgiana Puşcaşu
    • 1
  • Patricio Martínez Barco
    • 1
  • Estela Saquete Boró
    • 1
  1. 1.Department of Software and Computing SystemsUniversity of AlicanteSpain

Personalised recommendations