@inproceedings{li-etal-2023-hw,
title = "{HW}-{TSC} at {IWSLT}2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation",
author = "Li, Zongyao and
Wu, Zhanglin and
Rao, Zhiqiang and
YuHao, Xie and
JiaXin, Guo and
Wei, Daimeng and
Shang, Hengchao and
Minghan, Wang and
Chen, Xiaoyu and
Yu, Zhengzhe and
ShaoJun, Li and
LiZhi, Lei and
Yang, Hao",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.14",
doi = "10.18653/v1/2023.iwslt-1.14",
pages = "187--193",
abstract = "This paper presents HW-TSC{'}s submissions to the IWSLT 2023 Offline Speech Translation task, including speech translation of talks from English to German, Chinese, and Japanese, respectively. We participate in all three conditions (constrained training, constrained with large language models training, and unconstrained training) with models of cascaded architectures. We use data enhancement, pre-training models and other means to improve the ASR quality, and R-Drop, deep model, domain data selection, etc. to improve the translation quality. Compared with last year{'}s best results, we achieve 2.1 BLEU improvement on the MuST-C English-German test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-hw">
<titleInfo>
<title>HW-TSC at IWSLT2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xie</namePart>
<namePart type="family">YuHao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guo</namePart>
<namePart type="family">JiaXin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Minghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengzhe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">ShaoJun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">LiZhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents HW-TSC’s submissions to the IWSLT 2023 Offline Speech Translation task, including speech translation of talks from English to German, Chinese, and Japanese, respectively. We participate in all three conditions (constrained training, constrained with large language models training, and unconstrained training) with models of cascaded architectures. We use data enhancement, pre-training models and other means to improve the ASR quality, and R-Drop, deep model, domain data selection, etc. to improve the translation quality. Compared with last year’s best results, we achieve 2.1 BLEU improvement on the MuST-C English-German test set.</abstract>
<identifier type="citekey">li-etal-2023-hw</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.14</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>187</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC at IWSLT2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation
%A Li, Zongyao
%A Wu, Zhanglin
%A Rao, Zhiqiang
%A YuHao, Xie
%A JiaXin, Guo
%A Wei, Daimeng
%A Shang, Hengchao
%A Minghan, Wang
%A Chen, Xiaoyu
%A Yu, Zhengzhe
%A ShaoJun, Li
%A LiZhi, Lei
%A Yang, Hao
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F li-etal-2023-hw
%X This paper presents HW-TSC’s submissions to the IWSLT 2023 Offline Speech Translation task, including speech translation of talks from English to German, Chinese, and Japanese, respectively. We participate in all three conditions (constrained training, constrained with large language models training, and unconstrained training) with models of cascaded architectures. We use data enhancement, pre-training models and other means to improve the ASR quality, and R-Drop, deep model, domain data selection, etc. to improve the translation quality. Compared with last year’s best results, we achieve 2.1 BLEU improvement on the MuST-C English-German test set.
%R 10.18653/v1/2023.iwslt-1.14
%U https://aclanthology.org/2023.iwslt-1.14
%U https://doi.org/10.18653/v1/2023.iwslt-1.14
%P 187-193
Markdown (Informal)
[HW-TSC at IWSLT2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation](https://aclanthology.org/2023.iwslt-1.14) (Li et al., IWSLT 2023)
ACL
- Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Xie YuHao, Guo JiaXin, Daimeng Wei, Hengchao Shang, Wang Minghan, Xiaoyu Chen, Zhengzhe Yu, Li ShaoJun, Lei LiZhi, and Hao Yang. 2023. HW-TSC at IWSLT2023: Break the Quality Ceiling of Offline Track via Pre-Training and Domain Adaptation. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 187–193, Toronto, Canada (in-person and online). Association for Computational Linguistics.