论文标题
WMT 2020无监督的机器翻译共享任务的LMU慕尼黑系统
The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
论文作者
论文摘要
本文描述了LMU慕尼黑对WMT 2020的无监督共享任务，以两个语言指示，德语<->上索尔比安。我们的核心无监督神经机器翻译（UNMT）系统遵循Chronopoulou等人的策略。 （2020年），使用单语言预处理的语言生成模型（在德语上），并在德语和上层索尔比亚语上对其进行微调，然后初始化UNMT模型，该模型接受了在线退缩培训。从无监督的统计机转换（USMT）系统获得的伪并行数据用于微调UNMT模型。我们还将BPE-Dropout应用于低资源（上层索尔比亚）数据以获得更强大的系统。我们还尝试了残留的适配器，并发现它们在上索尔比亚>德国方向上有用。我们探索在倒退和课程中学习的采样，以更有原则的方式使用SMT翻译。最后，我们整合了表现最佳的系统，并在德国 - >上索尔比亚人的BLEU得分为32.4，而上索尔比亚 - >德国人则达到35.2。
This paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions, German<->Upper Sorbian. Our core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al. (2020), using a monolingual pretrained language generation model (on German) and fine-tuning it on both German and Upper Sorbian, before initializing a UNMT model, which is trained with online backtranslation. Pseudo-parallel data obtained from an unsupervised statistical machine translation (USMT) system is used to fine-tune the UNMT model. We also apply BPE-Dropout to the low resource (Upper Sorbian) data to obtain a more robust system. We additionally experiment with residual adapters and find them useful in the Upper Sorbian->German direction. We explore sampling during backtranslation and curriculum learning to use SMT translations in a more principled way. Finally, we ensemble our best-performing systems and reach a BLEU score of 32.4 on German->Upper Sorbian and 35.2 on Upper Sorbian->German.
