Adaptive Attention Span in Transformers

Association for Computational Linguistics (ACL)


We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while maintaining control over their memory footprint and computational time. We show the effectiveness of our approach on the task of character level language modeling, where we achieve state-of-the-art performances on text8 and enwiki8 by using a maximum context of 8k characters.

Latest Publications

Log-structured Protocols in Delos

Mahesh Balakrishnan, Mahesh Balakrishnan, Mihir Dharamshi, Jason Flinn, David Geraghty, Santosh Ghosh, Filip Gruszczynski, Ahmed Jafri, Jun Li, Jingming Liu, Suyog Mapara, Rajeev Nagar, Ivailo Nedelchev, Francois Richard, Chen Shen, Yee Jiun Song, Rounak Tibrewal, Vidhya Venkat, Ahmed Yossef, Ali Zaveri