A lot of information is hidden in foreign language text, making multilingual information extraction tools – and applications that allow cross-lingual information access – particularly useful. Only a few system developers offer their products for more than two or three languages. Typically, they develop the tools for one language and then adapt them to the others. Information on guidelines how to produce highly multilingual applications with the least possible effort is scarce. Due to the multinational character of the European institutions, the Text Mining applications developed at the Joint Research Centre (JRC) had to be planned with the multilinguality requirements in mind. The purpose of this chapter is to present the design principles behind the in-house developments and to show a number of different applications that are built according to these guidelines. The results of the text analysis applications presented here are visible on the publicly accessible multilingual news gathering, analysis and exploration tool NewsExplorer.

NewsExplorer currently covers 19 languages. It is publicly accessible at http://press.jrc.it/NewsExplorer.