University of Tsukuba’s Machine Translation System for IWSLT20 Open Domain Translation Task

Hongyi Cui, Yizhen Wei, Shohei Iida, Takehito Utsuro, Masaaki Nagata


Abstract
In this paper, we introduce University of Tsukuba’s submission to the IWSLT20 Open Domain Translation Task. We participate in both Chinese→Japanese and Japanese→Chinese directions. For both directions, our machine translation systems are based on the Transformer architecture. Several techniques are integrated in order to boost the performance of our models: data filtering, large-scale noised training, model ensemble, reranking and postprocessing. Consequently, our efforts achieve 33.0 BLEU scores for Chinese→Japanese translation and 32.3 BLEU scores for Japanese→Chinese translation.
Anthology ID:
2020.iwslt-1.17
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
145–148
Language:
URL:
https://aclanthology.org/2020.iwslt-1.17
DOI:
10.18653/v1/2020.iwslt-1.17
Bibkey:
Cite (ACL):
Hongyi Cui, Yizhen Wei, Shohei Iida, Takehito Utsuro, and Masaaki Nagata. 2020. University of Tsukuba’s Machine Translation System for IWSLT20 Open Domain Translation Task. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 145–148, Online. Association for Computational Linguistics.
Cite (Informal):
University of Tsukuba’s Machine Translation System for IWSLT20 Open Domain Translation Task (Cui et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.17.pdf
Video:
 http://slideslive.com/38929619