SAS: Self-Augmentation Strategy for Language Model Pre-training


  • Yifei Xu University of California, Los Angeles
  • Jingqiao Zhang Alibaba Group
  • Ru He Alibaba Group
  • Liangzhu Ge Alibaba Group
  • Chao Yang Alibaba Group
  • Cheng Yang Alibaba Group
  • Ying Nian Wu University of California, Los Angeles



Speech & Natural Language Processing (SNLP)


The core of self-supervised learning for pre-training language models includes pre-training task design as well as appropriate data augmentation. Most data augmentations in language model pre-training are context-independent. A seminal contextualized augmentation was recently proposed in ELECTRA and achieved state-of-the-art performance by introducing an auxiliary generation network (generator) to produce contextualized data augmentation for the training of a main discrimination network (discriminator). This design, however, introduces extra computation cost of the generator and a need to adjust the relative capability between the generator and the discriminator. In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs. Essentially, this strategy eliminates a separate generator and uses the single network to jointly conduct two pre-training tasks with MLM (Masked Language Modeling) and RTD (Replaced Token Detection) heads. It avoids the challenge to search for an appropriate size of the generator, which is critical to the performance as evidenced in ELECTRA and its subsequent variant models. In addition, SAS is a general strategy that can be seamlessly combined with many new techniques emerging recently or in the future, such as the disentangled attention mechanism from DeBERTa. Our experiments show that SAS is able to outperform ELECTRA and other state-of-the-art models in the GLUE tasks with similar or less computation cost.




How to Cite

Xu, Y., Zhang, J., He, R., Ge, L., Yang, C., Yang, C., & Wu, Y. N. (2022). SAS: Self-Augmentation Strategy for Language Model Pre-training. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11586-11594.



AAAI Technical Track on Speech and Natural Language Processing