Advertisement

The LIMSI Multilingual, Multitask QAst System

  • Sophie Rosset
  • Olivier Galibert
  • Guillaume Bernard
  • Eric Bilinski
  • Gilles Adda
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5706)

Abstract

In this paper, we present the LIMSI question-answering system which participated to the Question Answering on speech transcripts 2008 evaluation. This systems is based on a complete and multi-level analysis of both queries and documents. It uses an automatically generated research descriptor. A score based on those descriptors is used to select documents and snippets. The extraction and scoring of candidate answers is based on proximity measurements within the research descriptor elements and a number of secondary factors. We participated to all the subtasks and submitted 18 runs (for 16 sub-tasks). The evaluation results for manual transcripts range from 31% to 45% for accuracy depending on the task and from 16 to 41% for automatic transcripts.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Déchelotte, D., Schwenk, H., Adda, G., Gauvain, J.-L.: Improved machine translation of speech-to-text outputs, Antwerp. Belgium (2007)Google Scholar
  2. 2.
    Rosset, S., Galibert, O., Adda, G., Bilinski, E.: The limsi qast systems: comparison between human and automatic rules generation for question-answering on speech transcriptions. In: IEEE ASRU (December 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sophie Rosset
    • 1
  • Olivier Galibert
    • 1
  • Guillaume Bernard
    • 1
  • Eric Bilinski
    • 1
  • Gilles Adda
    • 1
  1. 1.Spoken Language Processing Group, LIMSI-CNRSFrance

Personalised recommendations