arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09491cs.CL
收藏

一种简单的大规模特征机器翻译判别训练方法

A simple discriminative training method for machine translation with large-scale features

Wright State University(莱特州立大学)

Tian Xia, Shaodan Zhai, Shaojun Wang

摘要:

在统计机器翻译中,当特征量较大时,裕度注入松弛算法(MIRA)是模型调整的主要方法,但其实现复杂度较高。我们介绍了一种新的方法,它把一个N-最好的列表作为一个置换和最小化Plackett-Luce损失的地面真值置换。大规模特征实验表明,该方法比MERT方法具有更好的鲁棒性,虽然只与MIRA匹配,但具有相对优势,易于实现。

英文摘要:

Margin infused relaxed algorithms (MIRAs) dominate model tuning in statistical machine translation in the case of large scale features, but also they are famous for the complexity in implementation. We introduce a new method, which regards an N-best list as a permutation and minimizes the Plackett-Luce loss of ground-truth permutations. Experiments with large-scale features demonstrate that, the new method is more robust than MERT; though it is only matchable with MIRAs, it has a comparatively advantage, easier to implement.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑