@inproceedings{pham-etal-2025-enhancing,
title = "Enhancing Named Entity Translation from Classical {C}hinese to {V}ietnamese in Traditional {V}ietnamese Medicine Domain: A Hybrid Masking and Dictionary-Augmented Approach",
author = "Pham, Nhu Vo Quynh and
Nguyen Phuc, Uyen Bao and
Nguyen, Long Hong Buu and
Dinh, Dien",
editor = "Flek, Lucie and
Narayan, Shashi and
Phương, L{\^e} Hồng and
Pei, Jiahuan",
booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.inlg-main.25/",
pages = "408--418",
abstract = "Vietnam{'}s traditional medical texts were historically written in Classical Chinese using Sino-Vietnamese pronunciations. As the Vietnamese language transitioned to a Latin-based national script and interest in integrating traditional medicine with modern healthcare grows, accurate translation of these texts has become increasingly important. However, the diversity of terminology and the complexity of translating medical entities into modern contexts pose significant challenges. To address this, we propose a method that fine-tunes large language models (LLMs) using augmented data and a Hybrid Entity Masking and Replacement (HEMR) strategy to improve named entity translation. We also introduce a parallel named entity translation dataset specifically curated for traditional Vietnamese medicine. Our evaluation across multiple LLMs shows that the proposed approach achieves a translation accuracy of 71.91{\%}, demonstrating its effectiveness. These results underscore the importance of incorporating named entity awareness into translation systems, particularly in low-resource and domain-specific settings like traditional Vietnamese medicine."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-etal-2025-enhancing">
<titleInfo>
<title>Enhancing Named Entity Translation from Classical Chinese to Vietnamese in Traditional Vietnamese Medicine Domain: A Hybrid Masking and Dictionary-Augmented Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nhu</namePart>
<namePart type="given">Vo</namePart>
<namePart type="given">Quynh</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uyen</namePart>
<namePart type="given">Bao</namePart>
<namePart type="family">Nguyen Phuc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="given">Hong</namePart>
<namePart type="given">Buu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dien</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="family">Narayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lê</namePart>
<namePart type="given">Hồng</namePart>
<namePart type="family">Phương</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vietnam’s traditional medical texts were historically written in Classical Chinese using Sino-Vietnamese pronunciations. As the Vietnamese language transitioned to a Latin-based national script and interest in integrating traditional medicine with modern healthcare grows, accurate translation of these texts has become increasingly important. However, the diversity of terminology and the complexity of translating medical entities into modern contexts pose significant challenges. To address this, we propose a method that fine-tunes large language models (LLMs) using augmented data and a Hybrid Entity Masking and Replacement (HEMR) strategy to improve named entity translation. We also introduce a parallel named entity translation dataset specifically curated for traditional Vietnamese medicine. Our evaluation across multiple LLMs shows that the proposed approach achieves a translation accuracy of 71.91%, demonstrating its effectiveness. These results underscore the importance of incorporating named entity awareness into translation systems, particularly in low-resource and domain-specific settings like traditional Vietnamese medicine.</abstract>
<identifier type="citekey">pham-etal-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.25/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>408</start>
<end>418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Named Entity Translation from Classical Chinese to Vietnamese in Traditional Vietnamese Medicine Domain: A Hybrid Masking and Dictionary-Augmented Approach
%A Pham, Nhu Vo Quynh
%A Nguyen Phuc, Uyen Bao
%A Nguyen, Long Hong Buu
%A Dinh, Dien
%Y Flek, Lucie
%Y Narayan, Shashi
%Y Phương, Lê Hồng
%Y Pei, Jiahuan
%S Proceedings of the 18th International Natural Language Generation Conference
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F pham-etal-2025-enhancing
%X Vietnam’s traditional medical texts were historically written in Classical Chinese using Sino-Vietnamese pronunciations. As the Vietnamese language transitioned to a Latin-based national script and interest in integrating traditional medicine with modern healthcare grows, accurate translation of these texts has become increasingly important. However, the diversity of terminology and the complexity of translating medical entities into modern contexts pose significant challenges. To address this, we propose a method that fine-tunes large language models (LLMs) using augmented data and a Hybrid Entity Masking and Replacement (HEMR) strategy to improve named entity translation. We also introduce a parallel named entity translation dataset specifically curated for traditional Vietnamese medicine. Our evaluation across multiple LLMs shows that the proposed approach achieves a translation accuracy of 71.91%, demonstrating its effectiveness. These results underscore the importance of incorporating named entity awareness into translation systems, particularly in low-resource and domain-specific settings like traditional Vietnamese medicine.
%U https://aclanthology.org/2025.inlg-main.25/
%P 408-418
Markdown (Informal)
[Enhancing Named Entity Translation from Classical Chinese to Vietnamese in Traditional Vietnamese Medicine Domain: A Hybrid Masking and Dictionary-Augmented Approach](https://aclanthology.org/2025.inlg-main.25/) (Pham et al., INLG 2025)
ACL