richardbaihe / paperreading

NLP papers
MIT License
2 stars 0 forks source link

ACL2020|Adaptive Attention Span in Transformers #30

Closed richardbaihe closed 4 years ago

richardbaihe commented 4 years ago

https://arxiv.org/pdf/1905.07799.pdf Adaptive attention span, experiments on enwiki8 and text8.

image image