论文标题
佩格：神经机器翻译的短语级对抗示例生成
PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation
论文作者
论文摘要
尽管端到端的神经机器翻译（NMT）取得了令人印象深刻的进步，但嘈杂的输入通常会导致模型变得脆弱和不稳定。事实证明，由于增强数据而产生对抗性示例对于减轻此问题很有用。对抗性示例生成（AEG）的现有方法是单词级或字符级别，它忽略了无处不在的短语结构。在本文中，我们提出了一个短语级对抗示例生成（PAEG）框架，以增强翻译模型的鲁棒性。我们的方法通过采用短语级替换策略，进一步改善了基于梯度的单词级AEG方法。我们在三个基准测试中验证了我们的方法，包括最不发达国家英语，IWSLT14德语 - 英语和WMT14英语 - 德国任务。实验结果表明，与以前的强基础相比，我们的方法显着提高了噪声的翻译性能和稳健性。
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to alleviate this problem. Existing methods for adversarial example generation (AEG) are word-level or character-level, which ignore the ubiquitous phrase structure. In this paper, we propose a Phrase-level Adversarial Example Generation (PAEG) framework to enhance the robustness of the translation model. Our method further improves the gradient-based word-level AEG method by adopting a phrase-level substitution strategy. We verify our method on three benchmarks, including LDC Chinese-English, IWSLT14 German-English, and WMT14 English-German tasks. Experimental results demonstrate that our approach significantly improves translation performance and robustness to noise compared to previous strong baselines.
