In this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine MachineudTranslation (MEMT) techniques, we do not rely on word alignments of output hypotheses, but prepare the input sentence for multi-engine processing. We do this by using a recursive decomposition algorithm that produces simple chunks as input to the MT engines. A consensus translationudis produced by combining the best chunk translations, selected through majority voting, a trigram language modeludscore and a confidence score assigned to each MT engine. We report statistically significant relative improvementsudof up to 9% BLEU score in experiments (English→Spanish) carried out on an 800-sentence test set extracted from the Penn-II Treebank.ud
展开▼
机译：在本文中，我们提出了一种新颖的方法，可以将多个MT引擎的输出组合成一个共识翻译。与以前的多引擎机器 udTranslation（MEMT）技术相比，我们不依赖输出假设的单词对齐，而是准备输入句子以进行多引擎处理。我们通过使用递归分解算法来做到这一点，该算法生成简单的块作为MT引擎的输入。共识翻译 udis是通过将最佳投票翻译，多数投票选择的Trigram语言模型 udscore和分配给每个MT引擎的置信度得分相结合而产生的。我们报告说，在从Penn-II树库中提取的800句测试集上进行的实验（英语→西班牙语）中，统计意义上的相对改进 udeu高达9％BLEU分数。 ud
展开▼
