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

arXiv: https://arxiv.org/abs/2212.00477 · HTML: https://mlsanity.com/paper/2212.00477/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 1 Dec 2022.

## Builds on (most cited first, 8 of 8)

- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement](https://mlsanity.com/paper/1802.06901/) (2018)
- [End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification](https://mlsanity.com/paper/1811.04719/) (2018)
- [Non-Autoregressive Machine Translation: It's Not as Fast as it Seems](https://mlsanity.com/paper/2205.01966/) (2022)
- [Findings of the Third Workshop on Neural Generation and Translation](https://mlsanity.com/paper/1910.13299/) (2019)
- [Findings of the Second Workshop on Neural Machine Translation and Generation](https://mlsanity.com/paper/1806.02940/) (2018)

## Abstract (arXiv)

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.