Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Heegon, Son, Seonil, Park, Jemin, Kim, Youngseok, Noh, Hyungjong, Lee, Yeonsoo
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence 68T50 I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2403.01479