RealFormer: Transformer Likes Residual Attention

12/21/2020

∙

by   Ruining He, et al.

∙

74

∙

share

Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple Residual Attention Layer Transformer architecture that significantly outperforms canonical Transformers on a spectrum of tasks including Masked Language Modeling, GLUE, and SQuAD. Qualitatively, RealFormer is easy to implement and requires minimal hyper-parameter tuning. It also stabilizes training and leads to models with sparser attentions. Code will be open-sourced upon paper acceptance.