The statistical approach to machine translation and a roadmap for speech translation

During the last few years, the statistical approach has found widespread use in machine translation, in particular for spoken language. In many comparative evaluations of automatic speech translation, the statistical approach was found to be significantly superior to the existing conventional approaches. The paper will present the main components of a statistical machine translation system (such as alignment and lexicon models, training procedure, generation of the target sentence) and summarize the progress made so far. We will conclude with a roadmap for future research on spoken language translation.