基于混淆网络解码的机器翻译多系统融合

在对当前几种较流行的统计机器翻译多系统融合方法分析的基础上,提出了一种改进的多系统融合框架,该框架集成了最小贝叶斯风险解码和多特征混淆网络解码两种技术。融合过程如下(1) 从多个翻译系统输出的 -best结果中,利用最小贝叶斯风险解码器选择一个风险最小的假设作为对齐参考;(2) 将其余的 -best假设结果与该参考对齐,从而构建混淆网络。多特征混淆网络基于对数线性模型,引入了更多有效的知识源参与最优路径选择,融合后的BLEU得分比融合前最好的单系统BLEU得分提高了2.19%。在对齐方法上,我们提出了一种改进的翻译错误率(Translation Error Rate, TER)准则——GIZA-TER准则,该准则可以对CN网络进行更有效的短语调序。实验中的显著性检验证明了本文方法的有效性。

Confusion Network Based System Combination for Statistical Machine Translation

Based on several popular methods of statistical machine translation combination, an improved multiple-system combination framework is proposed. This framework integrates Minimum Bayes-Risk (MBR) decoding and multi-feature Confusion Network (CN) decoding techniques with the following steps(1)MBR decoding technique is used to select the hypothesis with minimum risk as an alignment reference from several N-best results produced by translation systems ; (2)CN is constructed by aligning the other hypotheses with the reference. Based on log-linear model, the CN introduces more knowledge sources into the selection of optimal path. Compared with the best system without combination, the proposed framework has 2.19% improvement in BLEU score. Inaddition, we present a modified Translation Edit Rate (TER)—GIZA-TER metric for CN alignment, which facilitates a more effective phrase re-ordering. The significance tests demonstrate the validness of the proposed methods.