SINAI experience at CLEF

This paper reports our work on CLEF and CrossLanguage Information Retrieval using CLEF resources. We aim to construct a highly languageindependent CLIR model. To accomplish this objective, several problems must be overcome: text translation or pseudo-translation and merging the obtained results for each language for a given query. Three issues of text-translation are investigated: the impact of translation probabilities, automatic multi-word recognition, and the generation of similarity thesauri from a Web corpus. Because the proposed model is query-translation driven, it is necessary to merge several monolingual results in a unique multilingual list of documents. To accomplish this task, we propose a new approach, which we call 2-step RSV, and we show that it performs better than more traditional approaches.