Fast Realization of Automatic Translation Systems for New Mission-Relevant Languages

Documents written in foreign languages are important in preparation of military operations or during these operations. Often not enough human translators and also no automatic tools for translating are available. This problem increases if the documents are written in less-learned languages. Then even less translators and no automatic translation tools are at hand. Therefore, there are little possibilities for the military analyst to get the information out of these foreign documents. If new deployments are planned or new languages for intelligence purposes are identified, the question arises, how the military can react agile to this language problem. In this paper we propose a concept to improve this situation. The main points of the concept include reducing the expectations for the quality of the translation and using the approach of statistical machine translation to rapidly produce new translation systems. The presented concept also includes organizational aspects, but the main focus in this paper is on technical aspects. As an example we show a translation system for the language pair Dari – German. We report about the corpus construction and the experiments to improve the translation system.