University of Évora in QA@CLEF-2004

Abstract

The approach followed by the University of Évora team when building a system for participation in the CLEF 2004 question answering task for Portuguese is described. The system is based on two steps: for each question, a first search selects a set of potentially relevant documents; each of these documents is then analysed to obtain a semantic representation and the answer to the initial query. This approach was applied to the QA@CLEF test set for Portuguese with interesting results that have allowed us to identify the strong and weak features of our system. © Springer-Verlag Berlin Heidelberg 2005.