In this paper, we propose an augmented dependency-to-string model to combine the merits of both the head-dependents relations at handling long distance reordering and the fixed and floating structures at handling local reordering. For this purpose, we first compactly represent both the head-dependent relation and the fixed and floating structures into translation rules; second, in decoding we build "on-the-fly" new translation rules from the compact translation rules that can incorporate non-syntactic phrases into translations, thus alleviate the non-syntactic phrase coverage problem of dependency-to-string translation (Xie et al., 2011). Large-scale experiments on Chinese-to-English translation show that our augmented dependency-to-string model gains significant improvement of averaged +0.85 BLEU scores on three test sets over the dependency-to-string model.
展开▼
机译：在本文中，我们提出了一个增强依赖性到串模型，以将头部相关关系的优点与处理长途重新排序和处理局部重新排序的固定和浮动结构相结合。 为此，我们首先将头依赖关系和固定和浮动结构紧凑地代表翻译规则; 其次，在解码中，我们从紧凑的翻译规则中建立“现场”的新转换规则，这些规则可以将非语法短语合并到翻译中，从而减轻了依赖性到字符串翻译的非句法短语覆盖问题（Xie Et al。，2011）。 关于汉语 - 英语翻译的大规模实验表明，我们的增强依赖性到串模型在依赖于串模型上三个测试集上的平均+0.85 BLEU分数的显着改进。
展开▼
