现在是Morphin' Time！用屈折扰动对抗语言歧视
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
摘要：
仅在完美的标准英语语料库上进行训练会使预先训练好的神经网络倾向于歧视来自非标准语言背景的少数民族（例如，非裔美国人方言英语、新加坡口语英语等）。我们扰乱单词的屈折形态，以制作看似合理且语义相似的对抗性示例，这些示例在流行的NLP模型中暴露了这些偏见，例如，BERT和Transformer，并表明，对抗微调他们为一个单一的时代显着提高鲁棒性，而不牺牲性能的干净的数据。
英文摘要：
Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.). We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
