Back to Search Start Over

RoChBert: Towards Robust BERT Fine-tuning for Chinese

Authors :
Zhang, Zihan
Li, Jinfeng
Shi, Ning
Yuan, Bo
Liu, Xiangyu
Zhang, Rong
Xue, Hui
Sun, Donghong
Zhang, Chao
Publication Year :
2022

Abstract

Despite of the superb performance on a wide range of tasks, pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. In this paper, we present RoChBERT, a framework to build more Robust BERT-based models by utilizing a more comprehensive adversarial graph to fuse Chinese phonetic and glyph features into pre-trained representations during fine-tuning. Inspired by curriculum learning, we further propose to augment the training dataset with adversarial texts in combination with intermediate samples. Extensive experiments demonstrate that RoChBERT outperforms previous methods in significant ways: (i) robust -- RoChBERT greatly improves the model robustness without sacrificing accuracy on benign texts. Specifically, the defense lowers the success rates of unlimited and limited attacks by 59.43% and 39.33% respectively, while remaining accuracy of 93.30%; (ii) flexible -- RoChBERT can easily extend to various language models to solve different downstream tasks with excellent performance; and (iii) efficient -- RoChBERT can be directly applied to the fine-tuning stage without pre-training language model from scratch, and the proposed data augmentation method is also low-cost.<br />Comment: Accepted by Findings of EMNLP 2022

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2210.15944
Document Type :
Working Paper