University of Alicante at GeoCLEF 2005

For the participation of the University of Alicante in the first cross-language Geographic Information Retrieval, we have developed a system made up of three modules. One of them is an Information Retrieval module and the others are Named Entity Recognition modules based on machine learning and based on knowledge. We have carried out several runs with different combinations of these modules for resolving the monolingual and bilingual tasks. The system obtained better result in monolingual task achieving an improvement between 48% and 69% above the average. The results are shown and discussed in the paper. Categories and Subject Descriptors H.3 [Information Storage and Retrieval]: H.3.3 Information Search and Retrieval General Terms Algorithms, Experimentation, Measurement, Performance Keywords Information Retrieval, Geographic Information Retrieval, Named Entity Recognition

• Type: Conference
• Year: 2005
• Where: CLEF
• Authors: Óscar Ferrández, Zornitsa Kozareva, Antonio Toral, Elisa Noguera, Andrés Montoyo, Rafael Muñoz, Fernando Llopis
• Keywords: CLEF 2005, Geographic Information Retrieval, Information Retrieval, Named Entity Recognition