HackerPapers

arXiv:1905.07799cs.LG

Adaptive Attention Span in Transformers

Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

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.

arXiv comments
Accepted to ACL 2019
Journal reference
DOI
Subjects
cs.LGMachine Learning stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Mar 2023 to Mar 2023.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. CoLT5: Faster Long-Range Transformers With Conditional Computation 1 comment

    • One can also make a model to learn the necessary context length for each layer and head to save a huge amount of FLOPs: https://arxiv.org/abs/1905.07799

      voxgenView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.