@inproceedings{ahmadnia-etal-2025-advancing,
title = "Advancing Clinical Translation in {N}epali through Fine-Tuned Multilingual Models",
author = "Ahmadnia, Benyamin and
Shaikh, Sumaiya and
Poudel, Bibek and
Mohammed, Shazan and
Hooshmand, Sahar",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.6/",
pages = "48--56",
abstract = "Low-resource Neural Machine Translation (NMT) remains a major challenge, particularly in high-stakes domains such as healthcare. This paper presents a domain-adapted pipeline for English-Nepali medical translation leveraging two state-of-the-art multilingual Large Language Models (LLMs): mBART and NLLB-200. A high-quality, domain-specific parallel corpus is curated, and both models are fine-tuned using PyTorch frameworks. Translation fidelity is assessed through a multi-metric evaluation strategy that combines BLEU, CHRF++, METEOR, BERTScore, COMET, and perplexity. Our experimental results show that NLLB-200 consistently outperforms mBART across surface-level and semantic metrics, achieving higher accuracy and lower hallucination rates in clinical settings. In addition, error profiling and ethical assessments are conducted to highlight challenges such as term omissions and cultural bias. This work underscores the viability of large-scale multilingual models in enhancing medical translation for low-resource languages and proposes actionable paths toward safer and more equitable MT deployment in healthcare."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadnia-etal-2025-advancing">
<titleInfo>
<title>Advancing Clinical Translation in Nepali through Fine-Tuned Multilingual Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benyamin</namePart>
<namePart type="family">Ahmadnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumaiya</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bibek</namePart>
<namePart type="family">Poudel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shazan</namePart>
<namePart type="family">Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Hooshmand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-resource Neural Machine Translation (NMT) remains a major challenge, particularly in high-stakes domains such as healthcare. This paper presents a domain-adapted pipeline for English-Nepali medical translation leveraging two state-of-the-art multilingual Large Language Models (LLMs): mBART and NLLB-200. A high-quality, domain-specific parallel corpus is curated, and both models are fine-tuned using PyTorch frameworks. Translation fidelity is assessed through a multi-metric evaluation strategy that combines BLEU, CHRF++, METEOR, BERTScore, COMET, and perplexity. Our experimental results show that NLLB-200 consistently outperforms mBART across surface-level and semantic metrics, achieving higher accuracy and lower hallucination rates in clinical settings. In addition, error profiling and ethical assessments are conducted to highlight challenges such as term omissions and cultural bias. This work underscores the viability of large-scale multilingual models in enhancing medical translation for low-resource languages and proposes actionable paths toward safer and more equitable MT deployment in healthcare.</abstract>
<identifier type="citekey">ahmadnia-etal-2025-advancing</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.6/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>48</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancing Clinical Translation in Nepali through Fine-Tuned Multilingual Models
%A Ahmadnia, Benyamin
%A Shaikh, Sumaiya
%A Poudel, Bibek
%A Mohammed, Shazan
%A Hooshmand, Sahar
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ahmadnia-etal-2025-advancing
%X Low-resource Neural Machine Translation (NMT) remains a major challenge, particularly in high-stakes domains such as healthcare. This paper presents a domain-adapted pipeline for English-Nepali medical translation leveraging two state-of-the-art multilingual Large Language Models (LLMs): mBART and NLLB-200. A high-quality, domain-specific parallel corpus is curated, and both models are fine-tuned using PyTorch frameworks. Translation fidelity is assessed through a multi-metric evaluation strategy that combines BLEU, CHRF++, METEOR, BERTScore, COMET, and perplexity. Our experimental results show that NLLB-200 consistently outperforms mBART across surface-level and semantic metrics, achieving higher accuracy and lower hallucination rates in clinical settings. In addition, error profiling and ethical assessments are conducted to highlight challenges such as term omissions and cultural bias. This work underscores the viability of large-scale multilingual models in enhancing medical translation for low-resource languages and proposes actionable paths toward safer and more equitable MT deployment in healthcare.
%U https://aclanthology.org/2025.ranlp-1.6/
%P 48-56
Markdown (Informal)
[Advancing Clinical Translation in Nepali through Fine-Tuned Multilingual Models](https://aclanthology.org/2025.ranlp-1.6/) (Ahmadnia et al., RANLP 2025)
ACL