|| Checking for direct PDF access through Ovid
In this article, several criteria and paradigms are described to measure the performance of spoken language systems developed in the framework of national and international research projects. These evaluations are carried out in the domain of spontaneous human-human interaction as supported by machine translation systems. They are also applied in the domain of spontaneous human-machine interaction typically used in information retrieval applications. Some evaluation paradigms are discussed in more detail. It is also shown that official performance tests and site-specific evaluation criteria are complementary in use.