Question Answering (QA) systems are of great interest to the Language Engineering community because they combine Information Retrieval and Natural Language Processing within the same task. QA systems receive natural language queries (and not keywords) as input, process large unstructured document collections, and return precise answers (and not documents) as output.

The NIST TREC QA tracks (this year is the seventh round) have stimulated progress in QA state-of-the-art, establishing widely accepted and standardized evaluation measures and requirements. Nevertheless, multilinguality has always been outside of the scope of the TREC QA evaluation exercises, which, up to now, have focused on systems for English.

Within the framework of the Cross Language Evaluation Forum (CLEF), a pilot track for non-English monolingual and cross-language QA systems was succesfully set up for the first time in Europe in 2003. Since then, three other campaigns have been carried out, recording a costant increase in the number of participants and in the results achieved.