Answering French Questions in English by Exploiting Results from Several Sources of Information

Brigitte Grau (1) , Gabriel Illouz (1) , Laura Monceaux (2) , Isabelle Robba (1) , Anne Vilnat (1) , Guillaume Bourdil (1) , Faïza Elkateb-Gara (1) , Olivier Ferret (3) , Benoît Mathieu (3)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 LINA - Laboratoire d'Informatique de Nantes Atlantique
3 LIC2M - Laboratoire Ingénierie de la Connaissance Multimédia Multilingue

Our bilingual QA system MUSCLEF is based on QALC, the monolingual system with which we have participated in the previous TREC, where our best results were obtained when we combined the results of several searches. First, QALC searched a reliable document collection for answers, and second the WEB. We kept this strategy for CLEF, returning two runs. In the first one, we modified QALC so as to handle multilinguality by translating the terms identified in the question. In the second run, we combined the results of the first run with those obtained by first translating the question, then applying the full QALC strategy i.e. searching both the collection and the WEB. The final evaluation confirms the fact that the best results are obtained by combining different sources of information.

Domaines: Traitement du texte et du document; Informatique et langage [cs.CL]

Brigitte Grau, Gabriel Illouz, Laura Monceaux, Isabelle Robba, Anne Vilnat, et al.. Answering French Questions in English by Exploiting Results from Several Sources of Information. 5th Workshop of the Cross-Language Evaluation Forum (CLEF 2004), 2005, Bath, United Kingdom. pp.470--481. ⟨hal-00444444⟩