The Ecological Footprint of Neural Machine Translation Systems

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

158 Downloads (Pure)

Abstract

Over the past decade, deep learning (DL) has led to significant advancements in various fields of artificial intelligence, including machine translation (MT). These advancements would not be possible without the ever-growing volumes of data and the hardware that allows large DL models to be trained efficiently. Due to the large amount of computing cores as well as dedicated memory, graphics processing units (GPUs) are a more effective hardware solution for training and inference with DL models than central processing units (CPUs). However, the former is very power demanding. The electrical power consumption has economical as well as ecological implications. This chapter focuses on the ecological footprint of neural MT systems. It starts from the power drain during the training of and the inference with neural MT models and moves towards the environment impact, in terms of carbon dioxide emissions. Different architectures (RNN and Transformer) and different GPUs (consumer-grate NVidia 1080Ti and workstation-grade NVidia P100) are compared. Then, the overall CO2 offload is calculated for Ireland and the Netherlands. The NMT models and their ecological impact are compared to common household appliances to draw a more clear picture. The last part of this chapter analyses quantization, a technique for reducing the size and complexity of models, as a way to reduce power consumption. As quantized models can run on CPUs, they present a power-efficient inference solution without depending on a GPU.
Original languageEnglish
Title of host publicationTowards Responsible Machine Translation
Subtitle of host publicationEthical and Legal Considerations in Machine Translation
Editors Helena Moniz, Carla Parra Escartín
Place of PublicationSpringer, Cham
PublisherSpringer Nature Switzerland AG
Chapter10
Pages185-213
Number of pages25
Volume4
ISBN (Electronic)978-3-031-14689-3
ISBN (Print)978-3-031-14688-6
DOIs
Publication statusPublished - 1 Jan 2023

Keywords

  • cs.CL
  • Neural Machine Translation
  • Power Consumption
  • Carbon Dioxide Emissions
  • GPU Comparison
  • LSTM

Fingerprint

Dive into the research topics of 'The Ecological Footprint of Neural Machine Translation Systems'. Together they form a unique fingerprint.

Cite this