@inproceedings{nigatu-etal-2025-viability,
title = "Viability of Machine Translation for Healthcare in Low-Resourced Languages",
author = "Nigatu, Hellina Hailu and
Mehandru, Nikita and
Abadi, Negasi Haile and
Gebremeskel, Blen and
Alaa, Ahmed and
Choudhury, Monojit",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.535/",
pages = "10595--10609",
ISBN = "979-8-89176-332-6",
abstract = "Machine Translation errors in high-stakes settings like healthcare pose unique risks that could lead to clinical harm. The challenges are even more pronounced for low-resourced languages where human translators are scarce and MT tools perform poorly. In this work, we provide a taxonomy of Machine Translation errors for the healthcare domain using a publicly available MT system. Preparing an evaluation dataset from pre-existing medical datasets, we conduct our study focusing on two low-resourced languages: Amharic and Tigrinya. Based on our error analysis and findings from prior work, we test two pre-translation interventions{--}namely, paraphrasing the source sentence and pivoting with a related language{--} for their effectiveness in reducing clinical risk. We find that MT errors for healthcare most commonly happen when the source sentence includes medical terminology and procedure descriptions, synonyms, figurative language, and word order differences. We find that pre-translation interventions are not effective in reducing clinical risk if the base translation model performs poorly. Based on our findings, we provide recommendations for improving MT for healthcare."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nigatu-etal-2025-viability">
<titleInfo>
<title>Viability of Machine Translation for Healthcare in Low-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hellina</namePart>
<namePart type="given">Hailu</namePart>
<namePart type="family">Nigatu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Mehandru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Negasi</namePart>
<namePart type="given">Haile</namePart>
<namePart type="family">Abadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Blen</namePart>
<namePart type="family">Gebremeskel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Alaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</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 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Machine Translation errors in high-stakes settings like healthcare pose unique risks that could lead to clinical harm. The challenges are even more pronounced for low-resourced languages where human translators are scarce and MT tools perform poorly. In this work, we provide a taxonomy of Machine Translation errors for the healthcare domain using a publicly available MT system. Preparing an evaluation dataset from pre-existing medical datasets, we conduct our study focusing on two low-resourced languages: Amharic and Tigrinya. Based on our error analysis and findings from prior work, we test two pre-translation interventions–namely, paraphrasing the source sentence and pivoting with a related language– for their effectiveness in reducing clinical risk. We find that MT errors for healthcare most commonly happen when the source sentence includes medical terminology and procedure descriptions, synonyms, figurative language, and word order differences. We find that pre-translation interventions are not effective in reducing clinical risk if the base translation model performs poorly. Based on our findings, we provide recommendations for improving MT for healthcare.</abstract>
<identifier type="citekey">nigatu-etal-2025-viability</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.535/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>10595</start>
<end>10609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Viability of Machine Translation for Healthcare in Low-Resourced Languages
%A Nigatu, Hellina Hailu
%A Mehandru, Nikita
%A Abadi, Negasi Haile
%A Gebremeskel, Blen
%A Alaa, Ahmed
%A Choudhury, Monojit
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F nigatu-etal-2025-viability
%X Machine Translation errors in high-stakes settings like healthcare pose unique risks that could lead to clinical harm. The challenges are even more pronounced for low-resourced languages where human translators are scarce and MT tools perform poorly. In this work, we provide a taxonomy of Machine Translation errors for the healthcare domain using a publicly available MT system. Preparing an evaluation dataset from pre-existing medical datasets, we conduct our study focusing on two low-resourced languages: Amharic and Tigrinya. Based on our error analysis and findings from prior work, we test two pre-translation interventions–namely, paraphrasing the source sentence and pivoting with a related language– for their effectiveness in reducing clinical risk. We find that MT errors for healthcare most commonly happen when the source sentence includes medical terminology and procedure descriptions, synonyms, figurative language, and word order differences. We find that pre-translation interventions are not effective in reducing clinical risk if the base translation model performs poorly. Based on our findings, we provide recommendations for improving MT for healthcare.
%U https://aclanthology.org/2025.emnlp-main.535/
%P 10595-10609
Markdown (Informal)
[Viability of Machine Translation for Healthcare in Low-Resourced Languages](https://aclanthology.org/2025.emnlp-main.535/) (Nigatu et al., EMNLP 2025)
ACL