mlsanityData to 7 Oct 2026

The NiuTrans Machine Translation Systems for WMT21

arXiv 2109.10485 ↗First posted 22 Sep 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including EnglishleftrightarrowChinese, Japanese, Russian, Icelandic and EnglishrightarrowHausa tasks. Our primary systems are built on several effective variants of Transformer, e.g., Transformer-DLCL, ODE-Transformer. We also utilize back-translation, knowledge distillation, post-ensemble, and iterative fine-tuning techniques to enhance the model performance further.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 22 Sep 2021.

Builds on

15 of 26 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  5. 2018Self-Attention with Relative Position Representationscited by 1,112
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  7. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  8. 2018Scaling Neural Machine Translationcited by 204
  9. 2017Ensemble Distillation for Neural Machine Translationcited by 39
  10. 2020Shallow-to-Deep Training for Neural Machine Translationcited by 36
  11. 2020Learning Light-Weight Translation Models from Deep Transformercited by 22
  12. 2020Facebook AI's WMT20 News Translation Task Submissioncited by 17
3 more
  1. 2021ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translationcited by 12
  2. 2020WeChat Neural Machine Translation Systems for WMT20cited by 11
  3. 2020The Volctrans Machine Translation System for WMT20cited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  2. 2022ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generationcited by 26
  3. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  4. 2022Extending the Subwording Model of Multilingual Pretrained Models for New Languagescited by 3