Accelerated DP based search for statistical translation
Accelerated DP based search for statistical translation
复制标题
DOI：
10.21437/eurospeech.1997-673
复制
发表时间：
1997-09
期刊：
影响因子：
--
通讯作者：
Christoph Tillmann;S. Vogel;H. Ney;A. Zubiaga;H. Sawaf
中科院分区：
文献类型：
--
作者：
Christoph Tillmann;S. Vogel;H. Ney;A. Zubiaga;H. Sawaf
在本文中，我们描述了一个快速搜索算法的统计翻译的基础上动态规划（DP）和目前的实验结果。该方法是基于这样的假设，即词对齐是单调的相对于在两种语言中的词序。为了减少这种方法的搜索e（cid：11）ort，我们引入了两种方法：e（cid：14）精确计算动态规划递归方程的加速技术和用于语音识别的波束搜索策略。在Verbmobil语料库上进行的实验测试表明，以翻译假设的数量来衡量的搜索空间减少了约230倍，而不影响翻译性能。
In this paper, we describe a fast search algorithm for statistical translation based on dynamic programming (DP) and present experimental results. The approach is based on the assumption that the word alignment is monotone with respect to the word order in both languages. To reduce the search e(cid:11)ort for this approach, we introduce two methods: an acceleration technique to e(cid:14)ciently compute the dynamic programming recursion equation and a beam search strategy as used in speech recognition. The experimental tests carried out on the Verbmobil corpus showed that the search space, measured by the number of translation hypotheses, is reduced by a factor of about 230 without a(cid:11)ecting the translation performance.