Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data, increasing the risk of learning spurious patterns. To address this challenge, we propose a target-side augmentation method, introducing a data augmentation (DA) model to generate many potential translations for each source document. Learning on these wider range translations, an MT model can learn a smoothed distribution, thereby reducing the risk of data sparsity. We demonstrate that the DA model, which estimates the posterior distribution, largely improves the MT performance, outperforming the previous best system by 2.30 s-BLEU on News and achieving new state-of-the-art on News and Europarl benchmarks. Our code is available at \url{https://github.com/baoguangsheng/target-side-augmentation}.

翻译：文档级机器翻译因输入长度较长且训练数据量较少，面临数据稀疏的挑战，这增加了学习伪模式的风险。为解决该问题，我们提出了一种面向目标端的增强方法，引入数据增强模型为每个源文档生成大量潜在翻译。通过学习这些更广泛的翻译结果，机器翻译模型能够学习平滑分布，从而降低数据稀疏风险。实验证明，估计后验分布的数据增强模型显著提升了翻译性能，在News数据集上较先前最佳系统提升2.30 s-BLEU，并在News和Europarl基准测试中达到当前最优水平。我们的代码开源于 \url{https://github.com/baoguangsheng/target-side-augmentation}。