Log In Sign Up

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

by   Jindřich Helcl, et al.

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 state-of-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.


page 1

page 2

page 3

page 4


CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

We present a non-autoregressive system submission to the WMT 22 Efficien...

ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation

We propose to train a non-autoregressive machine translation model to mi...

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

Autoregressive decoding is the only part of sequence-to-sequence models ...

Can Multilinguality benefit Non-autoregressive Machine Translation?

Non-autoregressive (NAR) machine translation has recently achieved signi...

Can Latent Alignments Improve Autoregressive Machine Translation?

Latent alignment objectives such as CTC and AXE significantly improve no...

Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Non-autoregressive (NAR) neural machine translation is usually done via ...

Autoregressive Models: What Are They Good For?

Autoregressive (AR) models have become a popular tool for unsupervised l...