Skip to content

MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers.

Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei

VenueA*ACL
Year2021
ProceedingsACL/IJCNLP (Findings)

Browse the full ACL paper archive.