Removing mem-reuse will not decrease the pretraining model performance for short text? - Githubissues

zihangdai / xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Apache License 2.0

6.18k stars 1.18k forks source link

Removing mem-reuse will not decrease the pretraining model performance for short text? #273

Open guotong1988 opened 4 years ago

guotong1988 commented 4 years ago

Am I right?