arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.07847cs.CLcs.LG
收藏

Meta回译

Meta Back-translation

Carnegie Mellon University(卡内基梅隆大学);Google AI(谷歌人工智能)

Hieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig

摘要:

反向翻译是一种通过产生伪并行数据来提高神经机器翻译~(NMT)性能的有效策略。然而,最近的一些研究发现,伪并行数据的更好的翻译质量并不一定会导致更好的最终翻译模型,而质量较低但更多样化的数据往往会产生更强的结果。在本文中,我们提出了一种新的方法来生成伪并行数据从一个预先训练的反向翻译模型。我们的方法是一种Meta学习算法,该算法适应预先训练的反向翻译模型,使得它生成的伪并行数据将训练正向翻译模型,以在验证集上表现良好。在我们对标准数据集WMT En-De'14和WMT En-Fr'14以及多语言翻译环境的评估中,我们的方法在强大的基线上取得了显着的改进。我们的代码将提供。

英文摘要:

Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality of the pseudo-parallel data does not necessarily lead to better final translation models, while lower-quality but more diverse data often yields stronger results. In this paper, we propose a novel method to generate pseudo-parallel data from a pre-trained back-translation model. Our method is a meta-learning algorithm which adapts a pre-trained back-translation model so that the pseudo-parallel data it generates would train a forward-translation model to do well on a validation set. In our evaluations in both the standard datasets WMT En-De'14 and WMT En-Fr'14, as well as a multilingual translation setting, our method leads to significant improvements over strong baselines. Our code will be made available.

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。

↑