BIT's system for AutoSimTrans 2021

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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper we introduce our Chinese-English simultaneous translation system participating in AutoSimTrans 2021. In simultaneous translation, translation quality and latency are both important. In order to reduce the translation latency, 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 development dataset show that our system performs better than the baseline system.

Original languageEnglish
Title of host publicationProceedings of the 2nd Workshop on Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, AutoSimTrans 2021
EditorsHua Wu, Colin Cherry, Liang Huang, Zhongjun He, Qun Liu, Maha Elbayad, Mark Liberman, Haifeng Wang, Mingbo Ma, Ruiqing Zhang
PublisherAssociation for Computational Linguistics (ACL)
Pages12-18
Number of pages7
ISBN (Electronic)9781954085299
Publication statusPublished - 2021
Event2nd Workshop on Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, AutoSimTrans 2021 - Virtual, Online
Duration: 10 Jun 2021 → …

Publication series

NameProceedings of the 2nd Workshop on Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, AutoSimTrans 2021

Conference

Conference2nd Workshop on Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, AutoSimTrans 2021
CityVirtual, Online
Period10/06/21 → …

Fingerprint

Dive into the research topics of 'BIT's system for AutoSimTrans 2021'. Together they form a unique fingerprint.

Cite this