The Volctrans Machine Translation System for WMT20

10/28/2020
by   Liwei Wu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/22/2021

The NiuTrans Machine Translation Systems for WMT21

This paper describes NiuTrans neural machine translation systems of the ...
research
10/12/2022

Improved Data Augmentation for Translation Suggestion

Translation suggestion (TS) models are used to automatically provide alt...
research
10/29/2020

Tilde at WMT 2020: News Task Systems

This paper describes Tilde's submission to the WMT2020 shared task on ne...
research
11/07/2019

Microsoft Research Asia's Systems for WMT19

We Microsoft Research Asia made submissions to 11 language directions in...
research
07/09/2019

NTT's Machine Translation Systems for WMT19 Robustness Task

This paper describes NTT's submission to the WMT19 robustness task. This...
research
05/12/2020

Simultaneous paraphrasing and translation by fine-tuning Transformer models

This paper describes the third place submission to the shared task on si...
research
11/03/2021

Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared task

This paper describes Lingua Custodia's submission to the WMT21 shared ta...

Please sign up or login with your details

Forgot password? Click here to reset