The AISP-SJTU Simultaneous Translation System for IWSLT 2022

Qinpei Zhu, Renshou Wu, Guangfeng Liu, Xinyu Zhu, Xingyu Chen, Yang Zhou, Qingliang Miao, Rui Wang, Kai Yu


Abstract
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task. We participate in the text-to-text and speech-to-text simultaneous translation from English to Mandarin Chinese. The training of the CAAT is improved by training across multiple values of right context window size, which achieves good online performance without setting a prior right context window size for training. For speech-to-text task, the best model we submitted achieves 25.87, 26.21, 26.45 BLEU in low, medium and high regimes on tst-COMMON, corresponding to 27.94, 28.31, 28.43 BLEU in text-to-text task.
Anthology ID:
2022.iwslt-1.16
Volume:
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
Month:
May
Year:
2022
Address:
Dublin, Ireland (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marta Costa-jussà
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
208–215
Language:
URL:
https://aclanthology.org/2022.iwslt-1.16
DOI:
10.18653/v1/2022.iwslt-1.16
Bibkey:
Cite (ACL):
Qinpei Zhu, Renshou Wu, Guangfeng Liu, Xinyu Zhu, Xingyu Chen, Yang Zhou, Qingliang Miao, Rui Wang, and Kai Yu. 2022. The AISP-SJTU Simultaneous Translation System for IWSLT 2022. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 208–215, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The AISP-SJTU Simultaneous Translation System for IWSLT 2022 (Zhu et al., IWSLT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.iwslt-1.16.pdf