论文标题
是吗啡的时间！用拐点扰动打击语言歧视
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
论文作者
论文摘要
仅对完美的标准英语语料库进行培训，易于预先训练的神经网络，以区分少数民族与非标准的语言背景（例如，非裔美国人白话英语，俗语的新加坡英语等）。我们扰动单词的弯曲形态，以制作出合理和语义上相似的对抗性示例，这些例子在流行的NLP模型（例如BERT和Transformer）中暴露了这些偏见，并表明对对手进行对方的微调可以显着改善单个时代的效果，而无需在清洁数据上牺牲稳健性。
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.
