Statistical MT has made great progress in the last few years, but current translation models are weak on re-ordering and target language fluency. Syntactic approaches seek to remedy these problems. In this paper, we take the framework for acquiring multi-level syntactic translation rules of (Galley et al., 2004) from aligned tree-string pairs, and present two main extensions of their approach: first, instead of merely computing a single derivation that minimally explains a sentence pair, we construct a large number of derivations that include contex-tually richer rules, and account for multiple interpretations of unaligned words. Second, we propose probability estimates and a training procedure for weighting these rules. We contrast different approaches on real examples, show that our estimates based on multiple derivations favor phrasal re-orderings that are linguistically better motivated, and establish that our larger rules provide a 3.6.3 BLEU point increase over minimal rules.
展开▼
机译：统计MT在过去几年中取得了长足的进步，但是当前的翻译模型在重新排序和目标语言流利性方面均较弱。句法方法试图解决这些问题。在本文中，我们采用了从对齐的树串对中获取（Galley et al。，2004）的多级句法转换规则的框架，并提出了其方法的两个主要扩展：第一，而不是仅计算单个推导为了最小化解释一个句子对，我们构造了大量派生词，包括从概念上讲更丰富的规则，并解释了未对齐单词的多种解释。其次，我们提出了概率估计和加权这些规则的训练程序。我们在实际示例中对比了不同的方法，表明我们基于多个推导的估计偏向于短语重新排序，这些短语在语言上有更好的动机，并且确定了我们的大规则比最小规则增加了3.6.3 BLEU点。
展开▼
