Imposing Constraints from the Source Tree on ITG Constraints for SMT
Imposing Constraints from the Source Tree on ITG Constraints for SMT
复制标题
DOI：
10.1587/transinf.e92.d.1762
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
H. Yamamoto;Hideo Okuma;E. Sumita
中科院分区：
文献类型：
--
作者：
H. Yamamoto;Hideo Okuma;E. Sumita
在目前的统计机器翻译中，错误的单词重排是最严重的问题之一。为了解决这个问题，许多词重排序约束技术已被提出。倒置转换文法（ITG）就是其中之一。在ITG约束下，目标端的词序是通过旋转源端二叉树的节点来获得的。在这些节点旋转中，不考虑源二叉树实例。因此，通过对ITG约束施加从源树导出的进一步约束，可以获得用于单词重排序的更强约束。例如，对于源单词序列{ a B c d }，ITG约束允许总共22个目标单词排序。然而，当源二叉树实例（（a B）（c d））被给定时，我们提出的“将源树强加于ITG”（IST-ITG）约束只允许八个字排序。我们提出的更强的约束，有效地抑制错误的单词顺序排列的单词顺序排列的数量减少。在我们使用NIST MT 08英汉翻译跟踪数据的IST-ITG实验中，与我们的基线条件相比，所提出的方法在字符BLEU-4（35.2到37.0）上提高了1.8分，CER降低了6.2%（74.1到67.9%）。
In the current statistical machine translation (SMT), erroneous word reordering is one of the most serious problems. To resolve this problem, many word-reordering constraint techniques have been proposed. Inversion transduction grammar (ITG) is one of these constraints. In ITG constraints, target-side word order is obtained by rotating nodes of the source-side binary tree. In these node rotations, the source binary tree instance is not considered. Therefore, stronger constraints for word reordering can be obtained by imposing further constraints derived from the source tree on the ITG constraints. For example, for the source word sequence { a b c d }, ITG constraints allow a total of twenty-two target word orderings. However, when the source binary tree instance ((a b) (c d)) is given, our proposed “imposing source tree on ITG” (IST-ITG) constraints allow only eight word orderings. The reduction in the number of word-order permutations by our proposed stronger constraints efficiently suppresses erroneous word orderings. In our experiments with IST-ITG using the NIST MT08 English-to-Chinese translation track's data, the proposed method resulted in a 1.8-points improvement in character BLEU-4 (35.2 to 37.0) and a 6.2% lower CER (74.1 to 67.9%) compared with our baseline condition.