What Can Machine Translation Learn from Speech Recognition? Franz Josef Och

The performance of machine translation technology after 50 years of development leaves much to be desired. There is a high demand for well performing and cheap MT systems for many language pairs and do-mains, which automatically adapt to rapidly changing terminology. We argue that for successful MT systems it will be crucial to apply data-driven methods, especially statis-tical machine translation. In addition, it will be very important to establish common test environments. This includes the availability of large parallel training corpora, well de-fined test corpora and standardized evalua-tion criteria. Thereby research results can be compared and this will open the possibility for more competition in MT research.