@inproceedings{hui-jun-2022-ussts,
title = "{USST}{'}s System for {A}uto{S}im{T}rans 2022",
author = "Hui, Zhu and
Jun, Yu",
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-1.7",
doi = "10.18653/v1/2022.autosimtrans-1.7",
pages = "43--49",
abstract = "This paper describes our submitted text-to-text Simultaneous translation (ST) system, which won the second place in the Chinese→English streaming translation task of AutoSimTrans 2022. Our baseline system is a BPE-based Transformer model trained with the PaddlePaddle framework. In our experiments, we employ data synthesis and ensemble approaches to enhance the base model. In order to bridge the gap between general domain and spoken domain, we select in-domain data from general corpus and mixed then with spoken corpus for mixed fine tuning. Finally, we adopt fixed wait-k policy to transfer our full-sentence translation model to simultaneous translation model. Experiments on the development data show that our system outperforms than the baseline system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hui-jun-2022-ussts">
<titleInfo>
<title>USST’s System for AutoSimTrans 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Jun</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 paper describes our submitted text-to-text Simultaneous translation (ST) system, which won the second place in the Chinese→English streaming translation task of AutoSimTrans 2022. Our baseline system is a BPE-based Transformer model trained with the PaddlePaddle framework. In our experiments, we employ data synthesis and ensemble approaches to enhance the base model. In order to bridge the gap between general domain and spoken domain, we select in-domain data from general corpus and mixed then with spoken corpus for mixed fine tuning. Finally, we adopt fixed wait-k policy to transfer our full-sentence translation model to simultaneous translation model. Experiments on the development data show that our system outperforms than the baseline system.</abstract>
<identifier type="citekey">hui-jun-2022-ussts</identifier>
<identifier type="doi">10.18653/v1/2022.autosimtrans-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.autosimtrans-1.7</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>43</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USST’s System for AutoSimTrans 2022
%A Hui, Zhu
%A Jun, Yu
%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 hui-jun-2022-ussts
%X This paper describes our submitted text-to-text Simultaneous translation (ST) system, which won the second place in the Chinese→English streaming translation task of AutoSimTrans 2022. Our baseline system is a BPE-based Transformer model trained with the PaddlePaddle framework. In our experiments, we employ data synthesis and ensemble approaches to enhance the base model. In order to bridge the gap between general domain and spoken domain, we select in-domain data from general corpus and mixed then with spoken corpus for mixed fine tuning. Finally, we adopt fixed wait-k policy to transfer our full-sentence translation model to simultaneous translation model. Experiments on the development data show that our system outperforms than the baseline system.
%R 10.18653/v1/2022.autosimtrans-1.7
%U https://aclanthology.org/2022.autosimtrans-1.7
%U https://doi.org/10.18653/v1/2022.autosimtrans-1.7
%P 43-49
Markdown (Informal)
[USST’s System for AutoSimTrans 2022](https://aclanthology.org/2022.autosimtrans-1.7) (Hui & Jun, AutoSimTrans 2022)
ACL
- Zhu Hui and Yu Jun. 2022. USST’s System for AutoSimTrans 2022. In Proceedings of the Third Workshop on Automatic Simultaneous Translation, pages 43–49, Online. Association for Computational Linguistics.