Energy and Policy Considerations for Deep Learning in NLP

ACL 2019
Pages: 3645 - 3650
Published: Jun 5, 2019
Abstract
Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data. These models have obtained notable gains in accuracy across many NLP tasks. However, these accuracy improvements depend on the availability of exceptionally large computational resources that necessitate similarly substantial energy consumption. As a result these models are costly to train and...
Paper Details
Title
Energy and Policy Considerations for Deep Learning in NLP
Published Date
Jun 5, 2019
Journal
Pages
3645 - 3650
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.