@inproceedings{e0c4c76c0c65479bb2f230e53cea71d3,
title = "BIT-Xiaomi{\textquoteright}s Simultaneous Translation System for AutoSimTrans 2022",
abstract = "This system paper describes the BIT-Xiaomi simultaneous translation system for Autosimtrans 2022 simultaneous translation challenge. We participated in three tracks: the Zh-En text-to-text track, the Zh-En audio-to-text track, and the En-Es test-to-text track. In our system, wait-k is utilized to train prefix-to-prefix translation models. We integrate streaming chunking to detect segmentation boundaries as the source streaming reading in. We further improve our system with data selection, data augmentation, and R-Drop training methods. Results show that our wait-k implementation outperforms the organizer{\textquoteright}s baseline by at most 8 BLEU score and our proposed streaming chunking method further improves by about 2 BLEU score in the low latency regime.",
author = "Mengge Liu and Xiang Li and Bao Chen and Yanzhi Tian and Tianwei Lan and Silin Li and Yuhang Guo and Jian Luan and Bin Wang",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 3rd Workshop on Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, AutoSimTrans 2022 ; Conference date: 15-07-2022 Through 16-07-2022",
year = "2022",
language = "English",
series = "AutoSimTrans 2022 - Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, Proceedings of the 3rd Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "34--42",
editor = "Julia Ive and Ruiqing Zhang",
booktitle = "AutoSimTrans 2022 - Automatic Simultaneous Translation Challenges, Recent Advances, and Future Directions, Proceedings of the 3rd Workshop",
address = "United States",
}