Ding, Z., Jiang, G., Zhang, S., Guo, L., & Lin, W. (2023). SKDBERT: Compressing BERT via Stochastic Knowledge Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 7414-7422. https://doi.org/10.1609/aaai.v37i6.25902