Multi-Path Transformer is Better: A Case Study on Neural Machine Translation. EMNLP (Findings) 2022.

Release time:2024-01-09

Hits:

First Author:: Ye Lin, Shuhan Zhou, Yanyang Li, Anxiang Ma, Tong Xiao, Jingbo Zhu.

Translation or Not:: no

Pre One:Learning Multiscale Transformer Models for Sequence Generation. ICML2022.
Next One:Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection. EMNLP (Findings) 2022.