Non-Autoregressive Machine Translation: It’s Not as Fast as it Seems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest in non-autoregressive (NAR) models, which promise faster translation. In parallel to the research on NAR models, there have been successful attempts to create optimized autoregressive models as part of the WMT shared task on efficient translation. In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a stateof-the-art NAR model and the autoregressive submissions to the shared task. We make the case for consistent evaluation of NAR models, and also for the importance of comparing NAR models with other widely used methods for improving efficiency. We run experiments with a connectionist-temporal-classification-based (CTC) NAR model implemented in C++ and compare it with AR models using wall clock times. Our results show that, although NAR models are faster on GPUs, with small batch sizes, they are almost always slower under more realistic usage conditions. We call for more realistic and extensive evaluation of NAR models in future work.
Original languageEnglish
Title of host publicationProceedings of The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
EditorsMarine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics (ACL)
Pages1780-1790
Number of pages11
ISBN (Electronic)978-1-955917-71-1
Publication statusPublished - 1 Jul 2022
Event2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics
- Seattle, United States
Duration: 10 Jul 202215 Jul 2022
https://2022.naacl.org/

Conference

Conference2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Abbreviated titleNAACL 2022
Country/TerritoryUnited States
CitySeattle
Period10/07/2215/07/22
Internet address

Fingerprint

Dive into the research topics of 'Non-Autoregressive Machine Translation: It’s Not as Fast as it Seems'. Together they form a unique fingerprint.

Cite this