The Volctrans Machine Translation System for WMT20
Not on the map. Why?
Abstract (arXiv)
This paper describes our VolcTrans system on WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer, with several variants (wider or deeper Transformers, dynamic convolutions). The final system includes text pre-process, data selection, synthetic data generation, advanced model ensemble, and multilingual pre-training.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Oct 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 2.
7 papers.
- 2021Survey of Low-Resource Machine Translationcited by 92
- 2021Bidimensional Leaderboards: Generate and Evaluate Language Hand in Handcited by 32
- 2022GigaST: A 10,000-hour Pseudo Speech Translation Corpuscited by 20
- 2021The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21cited by 14
- 2022Onception: Active Learning with Expert Advice for Real World Machine Translationcited by 5
- 2021The NiuTrans Machine Translation Systems for WMT21cited by 4
- 2021The Volctrans Neural Speech Translation System for IWSLT 2021cited by 3
- 2022GigaST: A 10,000-hour Pseudo Speech Translation Corpus8 Apr 2022
- 2022Onception: Active Learning with Expert Advice for Real World Machine Translation9 Mar 2022
- 2021Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand8 Dec 2021
- 2021The Volctrans GLAT System: Non-autoregressive Translation Meets WMT2123 Sep 2021
- 2021The NiuTrans Machine Translation Systems for WMT2122 Sep 2021
- 2021Survey of Low-Resource Machine Translation1 Sep 2021
- 2021The Volctrans Neural Speech Translation System for IWSLT 202116 May 2021