@inproceedings{layerwisepruningoftransformerattention,
  title = {Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling},
  author = {Kyuhong Shim and Iksoo Choi and Wonyong Sung and Jungwook Choi},
  year = {2021},
  booktitle = {2021 18th International SoC Design Conference (ISOCC) 2021 11},
  eprint = {2110.03252},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.03252v1},
}