Comparison and Evaluation of Two Approaches of a Multilayered QA System Applied to Temporality

  • E. Saquete
  • R. Muñoz
  • P. Martínez-Barco
  • J. L. Vicedo
Conference paper

DOI: 10.1007/978-3-540-30228-5_9

Part of the Lecture Notes in Computer Science book series (LNCS, volume 3230)
Cite this paper as:
Saquete E., Muñoz R., Martínez-Barco P., Vicedo J.L. (2004) Comparison and Evaluation of Two Approaches of a Multilayered QA System Applied to Temporality. In: Vicedo J.L., Martínez-Barco P., Muńoz R., Saiz Noeda M. (eds) Advances in Natural Language Processing. Lecture Notes in Computer Science, vol 3230. Springer, Berlin, Heidelberg

Abstract

This paper compares two approaches to a multilayered Question Answering (QA) architecture suitable for enhancing current QA capabilities with the possibility of processing complex questions. That is, questions whose answer needs to be gathered from pieces of factual information that is scattered in different documents. Specifically, we have designed a layer oriented to process the different types of temporal questions. In the first approach, complex temporal questions are decomposed into simple questions, according to the temporal relations expressed in the original question. In the same way, the answers of each resulting simple question are recomposed, fulfilling the temporal restrictions of the original complex question. In the second approach, temporal information is added to the sub-questions before being processed. Evaluation results show that the second approach outperforms the first one in a 30%.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • E. Saquete
    • 1
  • R. Muñoz
    • 1
  • P. Martínez-Barco
    • 1
  • J. L. Vicedo
    • 1
  1. 1.Grupo de investigación del Procesamiento del Lenguaje y Sistemas de Información, Departamento de Lenguajes y Sistemas InformáticosUniversidad de AlicanteAlicanteSpain

Personalised recommendations