Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT

arxiv(2020)

引用 96|浏览156
暂无评分
摘要
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, however, how the models will perform in realistic scenarios where \textit{natural rather than malicious} adversarial instances often exist. This work systematically explores the robustness of BERT, the state-of-the-art Transformer-style model in NLP, in dealing with noisy data, particularly mistakes in typing the keyboard, that occur inadvertently. Intensive experiments on sentiment analysis and question answering benchmarks indicate that: (i) Typos in various words of a sentence do not influence equally. The typos in informative words make severer damages; (ii) Mistype is the most damaging factor, compared with inserting, deleting, etc.; (iii) Humans and machines have different focuses on recognizing adversarial attacks.
更多
查看译文
关键词
adversarial samples,misspellings!,robust,nature,adv-bert
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要