Creating a Dutch testbed to evaluate the retrieval from textual databases

This paper describes the first large-scale evaluation of information retrieval systems using Dutch documents and queries. We describe in detail the characteristics of the Dutch test data, which is part of the official CLEF multilingual texttual database, and give an overview of the experimental results of companies and research institutions that participated in the first official Dutch CLEF experiments. Judging from these experiments, the handling of language-specific issues of Dutch, like for instance simple morphology and compound nouns, significantly improves the performance of information retrieval systems in many cases. Careful examination of the test collection shows that it serves as a reliable tool for the evaluation of information retrieval systems in the future.