Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity

Haoran Xu, Maha Elbayad, Kenton Murray, Jean Maillard, Vedanuj Goswami

Findings: Machine Translation Findings Paper

Poster_Demo_Industry_Findings Virtual 3: Machine Translation (Poster)
Conference Room: Virtual-Gathertown
Conference Time: December 08, 16:00-17:30 (+08) (Asia/Singapore)
Global Time: December 08, Poster_Demo_Industry_Findings Virtual 3 (08:00-09:30 UTC)
TLDR:
You can open the #paper-2454 channel in a separate window.
Abstract: