arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.09006cs.CL
收藏

神经机器翻译中的难词定向回译抽样

Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation

Informatics Institute, University of Amsterdam(阿姆斯特丹大学信息学研究所)

Marzieh Fadaee, Christof Monz

摘要:

神经机器翻译使用并行和合成数据的组合,为几种语言对实现了最先进的性能。合成数据通常通过使用反向翻译模型从单语数据中随机采样的句子进行反向翻译来生成。虽然回译在许多情况下被证明是非常有效的,但原因尚不完全清楚。在这项工作中,我们探索了反向翻译的不同方面,并表明在训练过程中具有高预测损失的单词从添加合成数据中受益最多。我们介绍了几种变化的采样策略,针对难以预测的话,使用预测损失和频率的话。此外,我们还针对难词的上下文和在上下文中相似的例句。WMT新闻翻译任务的实验结果表明,我们的方法提高了翻译质量高达1.7和1.2 Bleu点回翻译使用随机抽样为德语-英语和英语-德语,分别。

英文摘要:

Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from monolingual data using a reverse translation model. While back-translation has been shown to be very effective in many cases, it is not entirely clear why. In this work, we explore different aspects of back-translation, and show that words with high prediction loss during training benefit most from the addition of synthetic data. We introduce several variations of sampling strategies targeting difficult-to-predict words using prediction losses and frequencies of words. In addition, we also target the contexts of difficult words and sample sentences that are similar in context. Experimental results for the WMT news translation task show that our method improves translation quality by up to 1.7 and 1.2 Bleu points over back-translation using random sampling for German-English and English-German, respectively.

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。

↑