Corpus

We used a subset of the EuroGOV corpus for our evaluation. This subset was composed by a set of Spanish Internet pages, originally obtained from European government-related sites.

In order to construct this corpus, for every page compiled in the EuroGOV corpus, we determine its language by using TexCat [15], a language identification program widely used. We construct our evaluation corpus with those documents identified as Spanish language.

The preprocessing process consisted of the elimination of punctuation symbols, Spanish stopwords, numbers, html tags, script codes and cascading style sheets codes.

For the evaluation of this corpus, a set of 134 queries was composed and refined, in order to provide gramatically correct ``English'' queries. Supervised queries (queries and related webpages) were created by the participants in the WebCLEF task, and the particular case of the queries were later reviewed and in some cases corrected in their English translation by the NLP Group at UNED. Queries were distributed in the following way: 67 homepages and 67 named page findings.

We applied a preprocessing phase to this set of queries. First, we used an online translation system in order to translate every query from English to Spanish. After that, an elimination of punctuation symbols, spanish stopwords and numbers was done.

We did not apply a rigorous method of translation, due to the fact that our main goal in our first participation in WebCLEF was to determine the quality of terms reduction in our CLIRS.