Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers.
Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu
Browse the full EMNLP paper archive.
Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu
Browse the full EMNLP paper archive.