Non-Autoregressive Neural Machine Translation: A Call for Clarity

by   Robin M. Schmidt, et al.

Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their translation quality still tends to be inferior to their autoregressive counterparts due to several issues involving output token interdependence. In this work, we take a step back and revisit several techniques that have been proposed for improving non-autoregressive translation models and compare their combined translation quality and speed implications under third-party testing environments. We provide novel insights for establishing strong baselines using length prediction or CTC-based architecture variants and contribute standardized BLEU, chrF++, and TER scores using sacreBLEU on four translation tasks, which crucially have been missing as inconsistencies in the use of tokenized BLEU lead to deviations of up to 1.7 BLEU points. Our open-sourced code is integrated into fairseq for reproducibility.


Fast Structured Decoding for Sequence Models

Autoregressive sequence models achieve state-of-the-art performance in d...

Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade

Fully non-autoregressive neural machine translation (NAT) is proposed to...

Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

Non-Autoregressive Neural Machine Translation (NAT) achieves significant...

Imitation Learning for Non-Autoregressive Neural Machine Translation

Non-autoregressive translation models (NAT) have achieved impressive inf...

Non-Autoregressive Machine Translation with Latent Alignments

This paper investigates two latent alignment models for non-autoregressi...

Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation

We propose an efficient inference procedure for non-autoregressive machi...

Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation

State-of-the-art neural machine translation models generate outputs auto...