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
Venues:
ACL | IWSLT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
145–148
Language:
URL:
https://www.aclweb.org/anthology/2020.iwslt-1.17
DOI:
10.18653/v1/2020.iwslt-1.17
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwslt-1.17.pdf
Video:
 http://slideslive.com/38929619