May, 2023
关于无监督 NMT 复制问题的训练进度与语言区分器损失
On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
Yihong Liu, Alexandra Chronopoulou, Hinrich Schütze, Alexander Fraser
TL;DR本文提出一种简单且有效的训练方法,通过增加语言鉴别器的损失,来约束中间翻译结果的语言,从而减轻低资源语言翻译中常见的抄袭问题,并提升翻译表现。