This is Appraise, an open-source system for manual evaluation of MT output


Dear colleague, the objective of this experiment is to compare translations produced by different Machine Translation approaches. The data you will be given consists of English into/from German/Czech sentences. Your task is to rank the list of translation candidates (may vary from 2 to 5) from the best to the worse given the source sentence and a reference translation both highlighted in boldface. The context around these sentences is only given to help you rank the candidates.