@inproceedings{merx-etal-2025-openwho,
title = "{O}pen{WHO}: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages",
author = "Merx, Raphael and
Suominen, Hanna and
Cohn, Trevor and
Vylomova, Ekaterina",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.8/",
pages = "142--160",
ISBN = "979-8-89176-341-8",
abstract = "Health machine translation (MT) is a high-stakes domain characterised by widespread deployment and domain-specific vocabulary. However, there is a lack of MT evaluation datasets for low-resource languages in the health domain. To address this gap, we introduce OpenWHO, a document-level parallel corpus of 2,978 documents and 26,824 sentences from the World Health Organization{'}s e-learning platform. Sourced from expert-authored, professionally translated materials shielded from web-crawling, OpenWHO spans a diverse range of over 20 languages, of which nine are low-resource. Leveraging this new resource, we evaluate modern large language models (LLMs) against traditional MT models. Our findings reveal that LLMs consistently outperform traditional MT models, with Gemini 2.5 Flash achieving a +4.79 ChrF point improvement over NLLB-54B on our low-resource test set. Further, we investigate how LLM context utilisation affects accuracy, finding that the benefits of document-level translation are most pronounced in specialised domains like health. We release the OpenWHO corpus to encourage further research into low-resource MT in the health domain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="merx-etal-2025-openwho">
<titleInfo>
<title>OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Merx</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Suominen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth Conference on Machine Translation</title>
</titleInfo>
<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">Philipp</namePart>
<namePart type="family">Koehn</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">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-341-8</identifier>
</relatedItem>
<abstract>Health machine translation (MT) is a high-stakes domain characterised by widespread deployment and domain-specific vocabulary. However, there is a lack of MT evaluation datasets for low-resource languages in the health domain. To address this gap, we introduce OpenWHO, a document-level parallel corpus of 2,978 documents and 26,824 sentences from the World Health Organization’s e-learning platform. Sourced from expert-authored, professionally translated materials shielded from web-crawling, OpenWHO spans a diverse range of over 20 languages, of which nine are low-resource. Leveraging this new resource, we evaluate modern large language models (LLMs) against traditional MT models. Our findings reveal that LLMs consistently outperform traditional MT models, with Gemini 2.5 Flash achieving a +4.79 ChrF point improvement over NLLB-54B on our low-resource test set. Further, we investigate how LLM context utilisation affects accuracy, finding that the benefits of document-level translation are most pronounced in specialised domains like health. We release the OpenWHO corpus to encourage further research into low-resource MT in the health domain.</abstract>
<identifier type="citekey">merx-etal-2025-openwho</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.8/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>142</start>
<end>160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages
%A Merx, Raphael
%A Suominen, Hanna
%A Cohn, Trevor
%A Vylomova, Ekaterina
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F merx-etal-2025-openwho
%X Health machine translation (MT) is a high-stakes domain characterised by widespread deployment and domain-specific vocabulary. However, there is a lack of MT evaluation datasets for low-resource languages in the health domain. To address this gap, we introduce OpenWHO, a document-level parallel corpus of 2,978 documents and 26,824 sentences from the World Health Organization’s e-learning platform. Sourced from expert-authored, professionally translated materials shielded from web-crawling, OpenWHO spans a diverse range of over 20 languages, of which nine are low-resource. Leveraging this new resource, we evaluate modern large language models (LLMs) against traditional MT models. Our findings reveal that LLMs consistently outperform traditional MT models, with Gemini 2.5 Flash achieving a +4.79 ChrF point improvement over NLLB-54B on our low-resource test set. Further, we investigate how LLM context utilisation affects accuracy, finding that the benefits of document-level translation are most pronounced in specialised domains like health. We release the OpenWHO corpus to encourage further research into low-resource MT in the health domain.
%U https://aclanthology.org/2025.wmt-1.8/
%P 142-160
Markdown (Informal)
[OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages](https://aclanthology.org/2025.wmt-1.8/) (Merx et al., WMT 2025)
ACL