论文标题
缺乏流利性正在伤害您的翻译模型
Lack of Fluency is Hurting Your Translation Model
论文作者
论文摘要
许多机器翻译模型经过双语语料库的培训，这些模型由两种不同语言的对齐句子对组成。但是，在双语语料库中的火车和测试集之间存在质量差异。虽然最多的火车句子是通过自动技术（例如爬行和句子对准方法）创建的，但通过人类考虑流利度来注释测试句子。我们假设训练语料库中的这种差异将产生翻译模型的性能下降。在这项工作中，我们定义\ textit {fluency噪声}以确定火车句子的哪些部分使它们看起来不自然。我们表明，可以通过基于预训练的分类器的简单基于梯度的方法来检测\ textit {fluency噪声}。通过在火车句子中删除\ textit {fluency噪声}，我们的最终模型优于WMT-14 de $ \ rightarrow $ en和ru $ \ rightarrow $ en上的基线。我们还显示了与反向翻译增强的兼容性，该增强通常用于提高翻译模型的流利度。最后，\ textit {fluency噪声}的定性分析提供了我们应该关注的观点的见解。
Many machine translation models are trained on bilingual corpus, which consist of aligned sentence pairs from two different languages with same semantic. However, there is a qualitative discrepancy between train and test set in bilingual corpus. While the most train sentences are created via automatic techniques such as crawling and sentence-alignment methods, the test sentences are annotated with the consideration of fluency by human. We suppose this discrepancy in training corpus will yield performance drop of translation model. In this work, we define \textit{fluency noise} to determine which parts of train sentences cause them to seem unnatural. We show that \textit{fluency noise} can be detected by simple gradient-based method with pre-trained classifier. By removing \textit{fluency noise} in train sentences, our final model outperforms the baseline on WMT-14 DE$\rightarrow$EN and RU$\rightarrow$EN. We also show the compatibility with back-translation augmentation, which has been commonly used to improve the fluency of the translation model. At last, the qualitative analysis of \textit{fluency noise} provides the insight of what points we should focus on.
