#NLP DEEP LEARNING MODS#
Cite (Informal): Energy and Policy Considerations for Deep Learning in NLP (Strubell et al., ACL 2019) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: Code additional community = "Energy and Policy Considerations for Deep Learning in ",īooktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
Association for Computational Linguistics. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3645–3650, Florence, Italy. Energy and Policy Considerations for Deep Learning in NLP.
Anthology ID: P19-1355 Volume: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics Month: July Year: 2019 Address: Florence, Italy Venue: ACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 3645–3650 Language: URL: DOI: 10.18653/v1/P19-1355 Bibkey: strubell-etal-2019-energy Cite (ACL): Emma Strubell, Ananya Ganesh, and Andrew McCallum. Based on these findings, we propose actionable recommendations to reduce costs and improve equity in NLP research and practice. In this paper we bring this issue to the attention of NLP researchers by quantifying the approximate financial and environmental costs of training a variety of recently successful neural network models for NLP. As a result these models are costly to train and develop, both financially, due to the cost of hardware and electricity or cloud compute time, and environmentally, due to the carbon footprint required to fuel modern tensor processing hardware. However, these accuracy improvements depend on the availability of exceptionally large computational resources that necessitate similarly substantial energy consumption. These models have obtained notable gains in accuracy across many NLP tasks.
Abstract Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data.
0 kommentar(er)
