AAN plus : Generalized Average Attention Network for Accelerating Neural Transformer

Zhang, B; Xiong, DY; Ge, YB; Yao, JF; Yue, H; Su, JS

Su, JS (通讯作者),Xiamen Univ, Sch Informat, Lab Digital Protect & Intelligent Proc Intangible, Minist Culture & Tourism, Xiamen 361005, Peoples R China.

JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2022; 75 (): 677