Sasha Rush (Cornell University) “Pretraining Without Attention” @ Hackerman Hall B17
Feb 3 @ 12:00 pm – 1:15 pm


Transformers are essential to pretraining. As we approach 5 years of BERT, the connection between attention as architecture and transfer learning remains key to this central thread in NLP. Other architectures such as CNNs and RNNs have been used to replicate pretraining results, but these either fail to reach the same accuracy or require supplemental attention layers. This work revisits the semanal BERT result and considers pretraining without attention. We consider replacing self-attention layers with recently developed approach for long-range sequence modeling and transformer architecture variants. Specifically, inspired by recent papers like the structured space space sequence model (S4), we use simple routing layers based on state-space models (SSM) and a bidirectional model architecture based on multiplicative gating. We discuss the results of the proposed Bidirectional Gated SSM (BiGS) and present a range of analysis into its properties. Results show that architecture does seem to have a notable impact on downstream performance and a different inductive bias that is worth exploring further.


Alexander “Sasha” Rush is an Associate Professor at Cornell Tech. His work is at the intersection of natural language processing and generative modeling with applications in text generation, efficient inference, and controllability. He has written several popular open-source software projects supporting NLP research and data science, and works part-time as a researcher at Hugging Face. He is the secretary of ICLR and developed software used to run virtual conferences during COVID. His work has received paper and demo awards at major NLP, visualization, and hardware conferences, an NSF Career Award, and a Sloan Fellowship. He tweets and blogs, mostly about coding and ML, at @srush_nlp.

Center for Language and Speech Processing