# DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation

arXiv: https://arxiv.org/abs/2206.02999 · HTML: https://mlsanity.com/paper/2206.02999/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement](https://mlsanity.com/paper/1802.06901/) (2018)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Understanding Knowledge Distillation in Non-autoregressive Machine Translation](https://mlsanity.com/paper/1911.02727/) (2019)
- [Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation](https://mlsanity.com/paper/2006.10369/) (2020)
- [Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2008.07905/) (2020)
- [Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/2012.15833/) (2020)
- [Non-Autoregressive Machine Translation with Latent Alignments](https://mlsanity.com/paper/2004.07437/) (2020)
- [FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow](https://mlsanity.com/paper/1909.02480/) (2019)
- [End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification](https://mlsanity.com/paper/1811.04719/) (2018)
- [Aligned Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2004.01655/) (2020)
- [Fast Structured Decoding for Sequence Models](https://mlsanity.com/paper/1910.11555/) (2019)
- [Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2106.05093/) (2021)
- [Non-Autoregressive Machine Translation with Auxiliary Regularization](https://mlsanity.com/paper/1902.10245/) (2019)
- [Directed Acyclic Transformer for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2205.07459/) (2022)
- [Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1911.09320/) (2019)
- [ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2005.00850/) (2020)
- [Semi-Autoregressive Training Improves Mask-Predict Decoding](https://mlsanity.com/paper/2001.08785/) (2020)
- [AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate](https://mlsanity.com/paper/2109.06481/) (2021)

## Abstract (arXiv)

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease the number of required steps to reach a certain translation quality. The distilled model enjoys the computational benefits of early iterations while preserving the enhancements from several iterative steps. DiMS relies on two models namely student and teacher. The student is optimized to predict the output of the teacher after multiple decoding steps while the teacher follows the student via a slow-moving average. The moving average keeps the teacher's knowledge updated and enhances the quality of the labels provided by the teacher. During inference, the student is used for translation and no additional computation is added. We verify the effectiveness of DiMS on various models obtaining 7.8 and 12.9 BLEU points improvements in single-step translation accuracy on distilled and raw versions of WMT'14 De-En.