Xu, R., F. Luo, C. Wang, B. Chang, J. Huang, S. Huang, and F. Huang. “From Dense to Sparse: Contrastive Pruning for Better Pre-Trained Language Model Compression”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 10, June 2022, pp. 11547-55, doi:10.1609/aaai.v36i10.21408.