@inproceedings{beyonddistillationtasklevelmixtureof,
  title = {Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference},
  author = {Sneha Kudugunta and Yanping Huang and Ankur Bapna and Maxim Krikun and Dmitry Lepikhin and Minh-Thang Luong and Orhan Firat},
  year = {2021},
  booktitle = {Findings (EMNLP) 2021 11},
  eprint = {2110.03742},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.03742v1},
}