AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation

Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young-Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sébastien Bubeck, Jianfeng Gao. AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation. In Anna Rogers, Jordan L. Boyd-Graber, Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023. pages 9116-9132, Association for Computational Linguistics, 2023. [doi]

@inproceedings{JawaharMLKALABG23,
  title = {AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation},
  author = {Ganesh Jawahar and Subhabrata Mukherjee and Xiaodong Liu and Young-Jin Kim and Muhammad Abdul-Mageed and Laks V. S. Lakshmanan and Ahmed Hassan Awadallah and Sébastien Bubeck and Jianfeng Gao},
  year = {2023},
  url = {https://aclanthology.org/2023.findings-acl.580},
  researchr = {https://researchr.org/publication/JawaharMLKALABG23},
  cites = {0},
  citedby = {0},
  pages = {9116-9132},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023},
  editor = {Anna Rogers and Jordan L. Boyd-Graber and Naoaki Okazaki},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-959429-62-3},
}