A Multi-agent Approach to Question Answering

  • Cássia Trojahn dos Santos
  • Paulo Quaresma
  • Irene Rodrigues
  • Renata Vieira
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3960)


In this paper we present a multi-agent approach to question answering for the Portuguese language. Our proposal is composed by three modules: (1) document and query processing; (2) ontology construction; and (3) answer generation. Each module is composed by multiple cooperative agents which adopt distinct strategies to generate its outputs and cooperate to create a global result. This approach allows the use of different strategies and the reduction of errors introduced by individual methods. The cooperation among the agents aims to reach better solutions in each step of the processing.


Query Processing Syntactic Structure Semantic Structure Question Answering Learning Agent 
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.
    Bick, E.: The Parsing System Palavras. Aarhus University Press (2000)Google Scholar
  2. 2.
    Chu-Carroll, J., Czuba, K., Prager, J.M., Ittycheriah, A.: In question answering, two heads are better than one. In: Proceedings of HLT-NAACL 2003 (2003)Google Scholar
  3. 3.
    Chu-Carroll, J., Prager, J.M., Welty, C.A., Czuba, K., Ferrucci, D.A.: A multi-strategy and multi-source approach to question answering. In: TREC (2002)Google Scholar
  4. 4.
    Dietterich, T.: Limitations on inductive learning. In: Proceedings of the Sixth International Workshop on Machine Learning, pp. 124–128 (1989)Google Scholar
  5. 5.
    Dietterich, T.: Machine learning research: Four current directions 4(18) (1997)Google Scholar
  6. 6.
    Dumais, S., Banko, M., Brill, E., Lin, J., Ng, A.: Web question answering: Is more always better? In: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 291–298 (2002)Google Scholar
  7. 7.
    Feng, Q., Cao, C., Sui, Y., Zheng, Y., Qin, Q.: Masaq: A multi-agent system for answering questions based on an encyclopedic knowledge base. In: Declarative Agent Languages and Technologies, DALT (2005)Google Scholar
  8. 8.
    Hammerton, J., Osborne, M., Armstrong, S., Daelemans, W.: Introduction to special issue on machine learning approaches to shallow parsing. Journal of Machine Learning Research, 551–558 (2002)Google Scholar
  9. 9.
    Haykin, S.: Redes Neurais Artificiais. Bookman (2001)Google Scholar
  10. 10.
    Hobbs, J., Stickel, M., Appelt, D., Martin, P.: Interpretation as abduction. Technical Report 499, Ravenswood (November 1990)Google Scholar
  11. 11.
    Jijkoun, V., de Rijke, M.: Answer selection in a multi-stream open domain question answering system. In: Proceedings of European Conference on Information Retrieval, pp. 99–111 (2004)Google Scholar
  12. 12.
    Kamp, H., Reyle, U.: From discourse to logic: an introduction to modeltheoretic semantics of natural language, formal logic and discourse representation theory (1993)Google Scholar
  13. 13.
    Megyesi, B.: Data-Driven Syntactic Analysis: Methods and Applications for Swedish. PhD thesis, University of Kungl Tekniska Hogskolan (2002)Google Scholar
  14. 14.
    Quaresma, P., Rodrigues, I.: A logic programming based approach to the qa@clef05 track. In: Peters, C., Gey, F.C., Gonzalo, J., Müller, H., Jones, G.J.F., Kluck, M., Magnini, B., de Rijke, M., Giampiccolo, D. (eds.) CLEF 2005. LNCS, vol. 4022, pp. 351–360. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. 15.
    Quinlan, J.R.: C4.5: Programs for machine learning (1993)Google Scholar
  16. 16.
    Rotaru, M., Litman, D.: Improving question answering for reading comprehension tests by combining multiple systems. In: Proceedings of the AAAI 2005 Workshop on Question Answering in Restricted Domains (2005)Google Scholar
  17. 17.
    Saias, J., Quaresma, P.: A methodology to create legal ontologies in a logic programming information retrieval system. In: Law and the Semantic Web, pp. 185–200 (2003)Google Scholar
  18. 18.
    Viktor, H., Arndt, H.: Combining data mining and human expertise for making decisions, sense and policies 4(2), 33–56 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Cássia Trojahn dos Santos
    • 1
  • Paulo Quaresma
    • 1
  • Irene Rodrigues
    • 1
  • Renata Vieira
    • 2
  1. 1.Departamento de InformáticaUniversidade de ÉvoraPortugal
  2. 2.Pós-Graduação em Computação AplicadaUniversidade do Vale do Rio dos SinosBrazil

Personalised recommendations