Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference Sneha Kudugunta author Yanping Huang author Ankur Bapna author Maxim Krikun author Dmitry Lepikhin author Minh-Thang Luong author Orhan Firat author 2021-11 text Findings of the Association for Computational Linguistics: EMNLP 2021 Marie-Francine Moens editor Xuanjing Huang editor Lucia Specia editor Scott Wen-tau Yih editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication kudugunta-etal-2021-beyond-distillation 10.18653/v1/2021.findings-emnlp.304 https://aclanthology.org/2021.findings-emnlp.304/ 2021-11 3577 3599