@inproceedings{park-etal-2023-varco,
title = "{VARCO}-{MT}: {NCSOFT}{'}s {WMT}{'}23 Terminology Shared Task Submission",
author = "Park, Geon Woo and
Lee, Junghwa and
Ren, Meiying and
Shindell, Allison and
Lee, Yeonsoo",
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-1.84",
doi = "10.18653/v1/2023.wmt-1.84",
pages = "919--925",
abstract = "A lack of consistency in terminology translation undermines quality of translation from even the best performing neural machine translation (NMT) models, especially in narrow domains like literature, medicine, and video game jargon. Dictionaries containing terminologies and their translations are often used to improve consistency but are difficult to construct and incorporate. We accompany our submissions to the WMT {`}23 Terminology Shared Task with a description of our experimental setup and procedure where we propose a framework of terminology-aware machine translation. Our framework comprises of an automatic terminology extraction process that constructs terminology-aware machine translation data in low-supervision settings and two model architectures with terminology constraints. Our models outperform baseline models by 21.51{\%}p and 19.36{\%}p in terminology recall respectively on the Chinese to English WMT{'}23 Terminology Shared Task test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-varco">
<titleInfo>
<title>VARCO-MT: NCSOFT’s WMT’23 Terminology Shared Task Submission</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geon</namePart>
<namePart type="given">Woo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junghwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meiying</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allison</namePart>
<namePart type="family">Shindell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeonsoo</namePart>
<namePart type="family">Lee</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>A lack of consistency in terminology translation undermines quality of translation from even the best performing neural machine translation (NMT) models, especially in narrow domains like literature, medicine, and video game jargon. Dictionaries containing terminologies and their translations are often used to improve consistency but are difficult to construct and incorporate. We accompany our submissions to the WMT ‘23 Terminology Shared Task with a description of our experimental setup and procedure where we propose a framework of terminology-aware machine translation. Our framework comprises of an automatic terminology extraction process that constructs terminology-aware machine translation data in low-supervision settings and two model architectures with terminology constraints. Our models outperform baseline models by 21.51%p and 19.36%p in terminology recall respectively on the Chinese to English WMT’23 Terminology Shared Task test data.</abstract>
<identifier type="citekey">park-etal-2023-varco</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.84</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.84</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>919</start>
<end>925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VARCO-MT: NCSOFT’s WMT’23 Terminology Shared Task Submission
%A Park, Geon Woo
%A Lee, Junghwa
%A Ren, Meiying
%A Shindell, Allison
%A Lee, Yeonsoo
%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 park-etal-2023-varco
%X A lack of consistency in terminology translation undermines quality of translation from even the best performing neural machine translation (NMT) models, especially in narrow domains like literature, medicine, and video game jargon. Dictionaries containing terminologies and their translations are often used to improve consistency but are difficult to construct and incorporate. We accompany our submissions to the WMT ‘23 Terminology Shared Task with a description of our experimental setup and procedure where we propose a framework of terminology-aware machine translation. Our framework comprises of an automatic terminology extraction process that constructs terminology-aware machine translation data in low-supervision settings and two model architectures with terminology constraints. Our models outperform baseline models by 21.51%p and 19.36%p in terminology recall respectively on the Chinese to English WMT’23 Terminology Shared Task test data.
%R 10.18653/v1/2023.wmt-1.84
%U https://aclanthology.org/2023.wmt-1.84
%U https://doi.org/10.18653/v1/2023.wmt-1.84
%P 919-925
Markdown (Informal)
[VARCO-MT: NCSOFT’s WMT’23 Terminology Shared Task Submission](https://aclanthology.org/2023.wmt-1.84) (Park et al., WMT 2023)
ACL