What Happened to Esfinge in 2007?

  • Luís Miguel Cabral
  • Luís Fernando Costa
  • Diana Santos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5152)


Esfinge is a general domain Portuguese question answering system which uses the information available on the Web as an additional resource when searching for answers. Other external resources and tools used are a broad coverage parser, a morphological analyser, a named entity recognizer and a Web-based database of word co-occurrences.

In this fourth participation in CLEF, in addition to the new challenges posed by the organization (topics and anaphors in questions and the use of Wikipedia to search and support answers), we experimented with a multiple question and multiple answer approach in QA.


Question answering Portuguese anaphor resolution question reformulation answer choice Wikipedia processing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sarmento, L.: BACO - A large database of text and co-occurrences. In: Calzolari, N., et al. (eds.) Proceedings of the 5th International Conference on Language Resources and Evaluation, Genoa, Italy, 22-28 May 2006, pp. 1787–1790 (2006)Google Scholar
  2. 2.
    Bick, E.: The Parsing System ”Palavras”: Automatic Grammatical Analysis of Portuguese in a Constraint Grammar Framework. Aarhus University Press (2000)Google Scholar
  3. 3.
    Santos, D., Costa, L.: QolA: fostering collaboration within QA. In: Peters, C., et al. (eds.) CLEF 2006. LNCS, vol. 4730, pp. 569–578. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Bertomeu, N., Uszkoreit, H., Frank, A., Krieger, H.U., Jörg, B.: Contextual phenomena and thematic relations in database QA dialogues: results from a Wizard-of-Oz Experiment. In: Proceedings of the HLT-NAACL 2006 Workshop on Interactive Question Answering (2006)Google Scholar
  5. 5.
    Cabral, L.M., Costa, L.F., Santos, D.: Esfinge at CLEF 2007: First steps in a multiple question and multiple answer approach. In: Nardi, A., Peters, C. (eds.) Working Notes for the CLEF 2007 Workshop, Budapest, Hungary, 19-21 September (2007)Google Scholar
  6. 6.
    Santos, D., Cardoso, N.: Portuguese at CLEF 2005: Reflections and Challenges. In: Peters, C., ed.: Cross Language Evaluation Forum: Working Notes for the CLEF 2005 Workshop, Vienna, Austria, 21-23 September (2005)Google Scholar
  7. 7.
    Mitkov, R.: Towards a more consistent and comprehensive evaluation of anaphora resolution algorithms and systems. In: Proceedings of the Discourse Anaphora and Anaphora Resolution Colloquium (DAARC 2000), Lancaster, UK, pp. 96–107 (2000)Google Scholar
  8. 8.
    Costa, L.: Question answering beyond CLEF document collections. In: Peters, C., et al. (eds.) CLEF 2006. LNCS, vol. 4730, pp. 405–414. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Luís Miguel Cabral
    • 1
  • Luís Fernando Costa
    • 1
  • Diana Santos
    • 1
  1. 1.Linguateca, Oslo node, SINTEF ICTNorway

Personalised recommendations