@inproceedings{liu-etal-2022-bit,
title = "{BIT}-Xiaomi{'}s System for {A}uto{S}im{T}rans 2022",
author = "Liu, Mengge and
Li, Xiang and
Chen, Bao and
Tian, Yanzhi and
Lan, Tianwei and
Li, Silin and
Guo, Yuhang and
Luan, Jian and
Wang, Bin",
editor = "Ive, Julia and
Zhang, Ruiqing",
booktitle = "Proceedings of the Third Workshop on Automatic Simultaneous Translation",
month = jul,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.autosimtrans-1.6",
doi = "10.18653/v1/2022.autosimtrans-1.6",
pages = "34--42",
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 employed to train prefix-to-prefix translation models. We integrate streaming chunking to detect boundaries as the source streaming read in. We further improve our system with data selection, data-augmentation and R-drop training methods. Results show that our wait-k implementation outperforms organizer{'}s baseline by 8 BLEU score at most, and our proposed streaming chunking method further improves about 2 BLEU in low latency regime.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-bit">
<titleInfo>
<title>BIT-Xiaomi’s System for AutoSimTrans 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengge</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianwei</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Automatic Simultaneous Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Ive</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiqing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 employed to train prefix-to-prefix translation models. We integrate streaming chunking to detect boundaries as the source streaming read in. We further improve our system with data selection, data-augmentation and R-drop training methods. Results show that our wait-k implementation outperforms organizer’s baseline by 8 BLEU score at most, and our proposed streaming chunking method further improves about 2 BLEU in low latency regime.</abstract>
<identifier type="citekey">liu-etal-2022-bit</identifier>
<identifier type="doi">10.18653/v1/2022.autosimtrans-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.autosimtrans-1.6</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>34</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BIT-Xiaomi’s System for AutoSimTrans 2022
%A Liu, Mengge
%A Li, Xiang
%A Chen, Bao
%A Tian, Yanzhi
%A Lan, Tianwei
%A Li, Silin
%A Guo, Yuhang
%A Luan, Jian
%A Wang, Bin
%Y Ive, Julia
%Y Zhang, Ruiqing
%S Proceedings of the Third Workshop on Automatic Simultaneous Translation
%D 2022
%8 July
%I Association for Computational Linguistics
%C Online
%F liu-etal-2022-bit
%X 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 employed to train prefix-to-prefix translation models. We integrate streaming chunking to detect boundaries as the source streaming read in. We further improve our system with data selection, data-augmentation and R-drop training methods. Results show that our wait-k implementation outperforms organizer’s baseline by 8 BLEU score at most, and our proposed streaming chunking method further improves about 2 BLEU in low latency regime.
%R 10.18653/v1/2022.autosimtrans-1.6
%U https://aclanthology.org/2022.autosimtrans-1.6
%U https://doi.org/10.18653/v1/2022.autosimtrans-1.6
%P 34-42
Markdown (Informal)
[BIT-Xiaomi’s System for AutoSimTrans 2022](https://aclanthology.org/2022.autosimtrans-1.6) (Liu et al., AutoSimTrans 2022)
ACL
- Mengge Liu, Xiang Li, Bao Chen, Yanzhi Tian, Tianwei Lan, Silin Li, Yuhang Guo, Jian Luan, and Bin Wang. 2022. BIT-Xiaomi’s System for AutoSimTrans 2022. In Proceedings of the Third Workshop on Automatic Simultaneous Translation, pages 34–42, Online. Association for Computational Linguistics.