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 2103.05951cs.CL
收藏

Zero Shot神经机器翻译的自学习

Self-Learning for Zero Shot Neural Machine Translation

University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)

Surafel M. Lakew, Matteo Negri, Marco Turchi

摘要:

神经机器翻译(NMT)方法采用单语数据,在资源丰富的条件下显示出稳定的改进。然而,使用现实世界中资源少的语言进行评价,仍然导致业绩不令人满意。这项工作提出了一种新的zero-shot NMT建模方法,学习没有现在的标准假设的枢轴语言共享并行数据与zero-shot源和目标语言。我们的方法基于三个阶段:从任何预先训练的NMT模型初始化,至少观察目标语言,利用目标单语数据增强源端,以及学习将初始模型优化为zero-shot对,其中后两个构成自学习循环。涉及四个不同的(在语言家庭,脚本和相关性方面)zero-shot对的实证研究结果表明,我们的方法的有效性与高达+5.93 BLEU改善对监督双语基线。与无监督NMT相比,即使在域不匹配的设置中也观察到一致的改进,证明了我们方法的可用性。

英文摘要:

Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance. This work proposes a novel zero-shot NMT modeling approach that learns without the now-standard assumption of a pivot language sharing parallel data with the zero-shot source and target languages. Our approach is based on three stages: initialization from any pre-trained NMT model observing at least the target language, augmentation of source sides leveraging target monolingual data, and learning to optimize the initial model to the zero-shot pair, where the latter two constitute a self-learning cycle. Empirical findings involving four diverse (in terms of a language family, script and relatedness) zero-shot pairs show the effectiveness of our approach with up to +5.93 BLEU improvement against a supervised bilingual baseline. Compared to unsupervised NMT, consistent improvements are observed even in a domain-mismatch setting, attesting to the usability of our method.

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。

↑