Introduction

The multi-language information published in Internet has experimented a big explosion in the last years. This fact, lead us to develop novel techniques to deal with the current cross-language feature of the World Wide Web (WWW). A common language scenario in which a user may be interested in information which is in a different language than their own native language would be when this user has some comprehension ability for a given language but s/he is not sufficiently proficient to confidently specify a search request in that language. Thus, a search system that can deal with this problem should be of a high benefit. The WWW is a natural setting for cross-lingual information retrieval and the European Union is a typical example of a multilingual scenario, where multiple users have to deal with information published in several languages. Therefore, evaluation environments for cross-lingual information retrieval systems are needed.

The Cross-Language Evaluation Forum (CLEF) has gathered a multi-lingual corpus and promotes the evaluation of cross-lingual information retrieval systems for different types of data [3]. WebCLEF is a particular task for the evaluation of such systems that deals with information on the Web [7]. A detailed discussion of the teams participation and the specific characteristics of the task proposed in the current WebCLEF may be found in [2]. In fact, they have proposed mainly one task for the evaluation of cross-lingual search engines: the Mixed Monolingual task. Thus, in this paper we are reporting the obtained results after the submission of one run to this competition.

We have used a text reduction with an enrichment process and, therefore, we organized this document in four sections. The next section describes the components of our search engine. In Section 3 a discussion of the corpus preprocessing as well as the obtained evaluation results are presented. Finally a conclusion of findings are given.