@inproceedings{kang-etal-2025-dacom,
title = "{D}a{C}o{M}: Strategies to Construct Domain-specific Low-resource Language Machine Translation Dataset",
author = "Kang, Junghoon and
Tak, Keunjoo and
Choi, Joungsu and
Kim, Myunghyun and
Jang, Junyoung and
Kang, Youjin",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.53/",
pages = "612--624",
abstract = "Translation of low-resource languages in industrial domains is essential for improving market productivity and ensuring foreign workers have better access to information. However, existing translators struggle with domain-specific terms, and there is a lack of expert annotators for dataset creation. In this work, we propose DaCoM, a methodology for collecting low-resource language pairs from industrial domains to address these challenges. DaCoM is a hybrid translation framework enabling effective data collection. The framework consists of a large language model and neural machine translation. Evaluation verifies existing models perform inadequately on DaCoM-created datasets, with up to 53.7 BLEURT points difference depending on domain inclusion. DaCoM is expected to address the lack of datasets for domain-specific low-resource languages by being easily pluggable into future state-of-the-art models and maintaining an industrial domain-agnostic approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2025-dacom">
<titleInfo>
<title>DaCoM: Strategies to Construct Domain-specific Low-resource Language Machine Translation Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junghoon</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keunjoo</namePart>
<namePart type="family">Tak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joungsu</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myunghyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyoung</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youjin</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translation of low-resource languages in industrial domains is essential for improving market productivity and ensuring foreign workers have better access to information. However, existing translators struggle with domain-specific terms, and there is a lack of expert annotators for dataset creation. In this work, we propose DaCoM, a methodology for collecting low-resource language pairs from industrial domains to address these challenges. DaCoM is a hybrid translation framework enabling effective data collection. The framework consists of a large language model and neural machine translation. Evaluation verifies existing models perform inadequately on DaCoM-created datasets, with up to 53.7 BLEURT points difference depending on domain inclusion. DaCoM is expected to address the lack of datasets for domain-specific low-resource languages by being easily pluggable into future state-of-the-art models and maintaining an industrial domain-agnostic approach.</abstract>
<identifier type="citekey">kang-etal-2025-dacom</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.53/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>612</start>
<end>624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaCoM: Strategies to Construct Domain-specific Low-resource Language Machine Translation Dataset
%A Kang, Junghoon
%A Tak, Keunjoo
%A Choi, Joungsu
%A Kim, Myunghyun
%A Jang, Junyoung
%A Kang, Youjin
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F kang-etal-2025-dacom
%X Translation of low-resource languages in industrial domains is essential for improving market productivity and ensuring foreign workers have better access to information. However, existing translators struggle with domain-specific terms, and there is a lack of expert annotators for dataset creation. In this work, we propose DaCoM, a methodology for collecting low-resource language pairs from industrial domains to address these challenges. DaCoM is a hybrid translation framework enabling effective data collection. The framework consists of a large language model and neural machine translation. Evaluation verifies existing models perform inadequately on DaCoM-created datasets, with up to 53.7 BLEURT points difference depending on domain inclusion. DaCoM is expected to address the lack of datasets for domain-specific low-resource languages by being easily pluggable into future state-of-the-art models and maintaining an industrial domain-agnostic approach.
%U https://aclanthology.org/2025.coling-industry.53/
%P 612-624
Markdown (Informal)
[DaCoM: Strategies to Construct Domain-specific Low-resource Language Machine Translation Dataset](https://aclanthology.org/2025.coling-industry.53/) (Kang et al., COLING 2025)
ACL