@inproceedings{zhang-2023-iol,
title = "{IOL} Research Machine Translation Systems for {WMT}23 General Machine Translation Shared Task",
author = "Zhang, Wenbo",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.19",
doi = "10.18653/v1/2023.wmt-1.19",
pages = "187--191",
abstract = "This paper describes the IOL Research team{'}s submission systems for the WMT23 general machine translation shared task. We participated in two language translation directions, including English-to-Chinese and Chinese-to-English. Our final primary submissions belong to constrained systems, which means for both translation directions we only use officially provided monolingual and bilingual data to train the translation systems. Our systems are based on Transformer architecture with pre-norm or deep-norm, which has been proven to be helpful for training deeper models. We employ methods such as back-translation, data diversification, domain fine-tuning and model ensemble to build our translation systems. An important aspect worth mentioning is our careful data cleaning process and the utilization of a substantial amount of monolingual data for data augmentation. Compared with the baseline system, our submissions have a large improvement in BLEU score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2023-iol">
<titleInfo>
<title>IOL Research Machine Translation Systems for WMT23 General Machine Translation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the IOL Research team’s submission systems for the WMT23 general machine translation shared task. We participated in two language translation directions, including English-to-Chinese and Chinese-to-English. Our final primary submissions belong to constrained systems, which means for both translation directions we only use officially provided monolingual and bilingual data to train the translation systems. Our systems are based on Transformer architecture with pre-norm or deep-norm, which has been proven to be helpful for training deeper models. We employ methods such as back-translation, data diversification, domain fine-tuning and model ensemble to build our translation systems. An important aspect worth mentioning is our careful data cleaning process and the utilization of a substantial amount of monolingual data for data augmentation. Compared with the baseline system, our submissions have a large improvement in BLEU score.</abstract>
<identifier type="citekey">zhang-2023-iol</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.19</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>187</start>
<end>191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IOL Research Machine Translation Systems for WMT23 General Machine Translation Shared Task
%A Zhang, Wenbo
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-2023-iol
%X This paper describes the IOL Research team’s submission systems for the WMT23 general machine translation shared task. We participated in two language translation directions, including English-to-Chinese and Chinese-to-English. Our final primary submissions belong to constrained systems, which means for both translation directions we only use officially provided monolingual and bilingual data to train the translation systems. Our systems are based on Transformer architecture with pre-norm or deep-norm, which has been proven to be helpful for training deeper models. We employ methods such as back-translation, data diversification, domain fine-tuning and model ensemble to build our translation systems. An important aspect worth mentioning is our careful data cleaning process and the utilization of a substantial amount of monolingual data for data augmentation. Compared with the baseline system, our submissions have a large improvement in BLEU score.
%R 10.18653/v1/2023.wmt-1.19
%U https://aclanthology.org/2023.wmt-1.19
%U https://doi.org/10.18653/v1/2023.wmt-1.19
%P 187-191
Markdown (Informal)
[IOL Research Machine Translation Systems for WMT23 General Machine Translation Shared Task](https://aclanthology.org/2023.wmt-1.19) (Zhang, WMT 2023)
ACL