Skip to content

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Authors: Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., et al. Year: 2019 ArXiv: https://arxiv.org/abs/1907.11692

Summary

RoBERTa improves BERT by modifying key hyperparameters and training procedures. It removes NSP objective, trains on larger data for longer, and uses dynamic masking patterns, achieving state-of-the-art on GLUE and SuperGLUE benchmarks.

Key Concepts

  • Improved training procedures over BERT
  • Removal of NSP objective
  • Dynamic masking patterns
  • Larger batch sizes and longer training
  • Better downstream task performance

Impact

RoBERTa showed that pre-training details matter as much as architecture. It set the standard for how to properly train transformer encoders and became the baseline for many subsequent improvements.


Citation:

@inproceedings{liu2019roberta,
  title={RoBERTa: A Robustly Optimized BERT Pretraining Approach},
  author={Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and others},
  booktitle={arXiv preprint arXiv:1907.11692},
  year={2019}
}