mlsanityData to 7 Oct 2026

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

arXiv 2212.00477 ↗First posted 1 Dec 2022cs.CLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 14 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

8 of 14 references.

References · 8

  1. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  2. 2017Non-Autoregressive Neural Machine Translationcited by 457
  3. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  4. 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 194
  5. 2018End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classificationcited by 72
  6. 2022Non-Autoregressive Machine Translation: It's Not as Fast as it Seemscited by 11
  7. 2019Findings of the Third Workshop on Neural Generation and Translationcited by 8
  8. 2018Findings of the Second Workshop on Neural Machine Translation and Generationcited by 5

Built on by

Not cited yet.