CASIA’s System for IWSLT 2020 Open Domain Translation

Qian Wang, Yuchen Liu, Cong Ma, Yu Lu, Yining Wang, Long Zhou, Yang Zhao, Jiajun Zhang, Chengqing Zong


Abstract
This paper describes the CASIA’s system for the IWSLT 2020 open domain translation task. This year we participate in both Chinese→Japanese and Japanese→Chinese translation tasks. Our system is neural machine translation system based on Transformer model. We augment the training data with knowledge distillation and back translation to improve the translation performance. Domain data classification and weighted domain model ensemble are introduced to generate the final translation result. We compare and analyze the performance on development data with different model settings and different data processing techniques.
Anthology ID:
2020.iwslt-1.15
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | IWSLT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
130–139
Language:
URL:
https://www.aclweb.org/anthology/2020.iwslt-1.15
DOI:
10.18653/v1/2020.iwslt-1.15
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwslt-1.15.pdf
Video:
 http://slideslive.com/38929589