Please use this identifier to cite or link to this item:
|Title: ||University of Évora in QA@CLEF-2004.|
|Authors: ||Quaresma, Paulo|
|Editors: ||Peters, Carol|
J. F. Jones, Gareth
|Keywords: ||Question Answer|
Processamento de lingua natural
|Issue Date: ||2005|
|Citation: || Paulo Quaresma, Luis Quintano, Irene Rodrigues, and Pedro Salgueiro. The university of E ́voraapproachtoqa@clef-2004.InC.Peters,P.Clough,J.Gonzalo,G.Jones,M.Kluck, and B. Magnini, editors, Multilingual Information Access for Text, Speech and Images, Lecture Notes in Computer Science LNCS 3491, pages 534–543. Springer, 2005. Revised and selected papers of the 5th Workshop of the Cross-Language Evaluation Forum, CLEF|
|Abstract: ||The approach followed by the University of E ́vora team in order to build a system able to participate in the QA-CLEF task is described.
The system is based in two steps: for each question, a first information retrieval task selects a set of potentially relevant documents; then, each of these documents is analysed trying to obtain their semantic represen- tation and the answer to the initial query.
The proposed approach was applied to the test set of the QA-CLEF for the Portuguese language and the obtained results were quite interest- ing and motivating and allowed the identification of strong and weak characteristics of the system.|
|Appears in Collections:||INF - Publicações - Capítulos de Livros|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.