arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15877cs.CLcs.AI
收藏

达罗毗荼语的无监督机器翻译

Unsupervised Machine Translation On Dravidian Languages

Maastricht University(马斯特里赫特大学)

Sai Koneru, Danni Liu, Jan Niehues

摘要:

无监督神经机器翻译(UNMT)特别有益于低资源语言,例如德拉维语系语言。然而,联合国MT系统往往在涉及实际低资源语言的现实情况下失败。最近的工作提出利用辅助并行数据,并取得了国家的最先进的成果。在这项工作中,我们专注于英语和卡纳达语,低资源达罗毗荼语之间的无监督翻译。我们还利用英语和其他相关的达罗毗荼语之间的辅助数据有限。我们表明,统一的书写系统是必不可少的,在无监督的翻译之间的达罗毗荼语。我们探索了几种使用辅助数据的模型架构,以最大限度地提高知识共享,并使UNMT对遥远的语言对。我们的实验表明,包括与我们的重点语言卡纳达语相似的辅助语言是至关重要的。此外,我们提出了一个度量来衡量语言相似性,并表明它作为一个很好的指标,选择辅助语言。

英文摘要:

Unsupervised neural machine translation (UNMT) is beneficial especially for low resource languages such as those from the Dravidian family. However, UNMT systems tend to fail in realistic scenarios involving actual low resource languages. Recent works propose to utilize auxiliary parallel data and have achieved state-of-the-art results. In this work, we focus on unsupervised translation between English and Kannada, a low resource Dravidian language. We additionally utilize a limited amount of auxiliary data between English and other related Dravidian languages. We show that unifying the writing systems is essential in unsupervised translation between the Dravidian languages. We explore several model architectures that use the auxiliary data in order to maximize knowledge sharing and enable UNMT for distant language pairs. Our experiments demonstrate that it is crucial to include auxiliary languages that are similar to our focal language, Kannada. Furthermore, we propose a metric to measure language similarity and show that it serves as a good indicator for selecting the auxiliary languages.

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。

↑