BIT’s system for AutoSimulTrans2021

Mengge Liu, Shuoying Chen, Minqin Li, Zhipeng Wang, Yuhang Guo


Abstract
In this paper we introduce our Chinese-English simultaneous translation system participating in AutoSimulTrans2021. In simultaneous translation, translation quality and delay are both important. In order to reduce the translation delay, we cut the streaming-input source sentence into segments and translate the segments before the full sentence is received. In order to obtain high-quality translations, we pre-train a translation model with adequate corpus and fine-tune the model with domain adaptation and sentence length adaptation. The experimental results on the evaluation data show that our system performs better than the baseline system.
Anthology ID:
2021.autosimtrans-1.2
Volume:
Proceedings of the Second Workshop on Automatic Simultaneous Translation
Month:
June
Year:
2021
Address:
Online
Venues:
AutoSimTrans | NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12–18
Language:
URL:
https://aclanthology.org/2021.autosimtrans-1.2
DOI:
10.18653/v1/2021.autosimtrans-1.2
Bibkey:
Cite (ACL):
Mengge Liu, Shuoying Chen, Minqin Li, Zhipeng Wang, and Yuhang Guo. 2021. BIT’s system for AutoSimulTrans2021. In Proceedings of the Second Workshop on Automatic Simultaneous Translation, pages 12–18, Online. Association for Computational Linguistics.
Cite (Informal):
BIT’s system for AutoSimulTrans2021 (Liu et al., AutoSimTrans 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.autosimtrans-1.2.pdf