@inproceedings{nguyen-etal-2025-serving,
title = "Serving the Underserved: Leveraging {BARTB}ahnar Language Model for Bahnaric-{V}ietnamese Translation",
author = "Nguyen, Long and
Le, Tran and
Nguyen, Huong and
Vo, Quynh and
Nguyen, Phong and
Quan, Tho",
editor = "Truong, Sang and
Putri, Rifki Afina and
Nguyen, Duc and
Wang, Angelina and
Ho, Daniel and
Oh, Alice and
Koyejo, Sanmi",
booktitle = "Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.lm4uc-1.5/",
doi = "10.18653/v1/2025.lm4uc-1.5",
pages = "32--41",
ISBN = "979-8-89176-242-8",
abstract = "The Bahnar people, one of Vietnam{'}s ethnic minorities, represent an underserved community with limited access to modern technologies. Developing an effective Bahnaric-Vietnamese translation system is essential for fostering linguistic exchange, preserving cultural heritage, and empowering local communities by bridging communication barriers. With advancements in Artificial Intelligence (AI), Neural Machine Translation (NMT) has achieved remarkable success across various language pairs. However, the low-resource nature of Bahnaric, characterized by data scarcity, vocabulary constraints, and the lack of parallel corpora, poses significant challenges to building an accurate and efficient translation system. To address these challenges, we propose a novel hybrid architecture for Bahnaric-Vietnamese translation, with BARTBahnar as its core language model. BARTBahnar is developed by continually training a pre-trained Vietnamese model, BARTPho, on augmented monolingual Bahnaric data, followed by fine-tuning on bilingual datasets. This transfer learning approach reduces training costs while effectively capturing linguistic similarities between the two languages. Additionally, we implement advanced data augmentation techniques to enrich and diversify training data, further enhancing BARTBahnar{'}s robustness and translation accuracy. Beyond leveraging the language model, our hybrid system integrates rule-based and statistical methods to improve translation quality. Experimental results show substantial improvements on bilingual Bahnaric-Vietnamese datasets, validating the effectiveness of our approach for low-resource translation. To support further research, we open-source our code and related materials at https://github.com/ura-hcmut/BARTBahnar."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-serving">
<titleInfo>
<title>Serving the Underserved: Leveraging BARTBahnar Language Model for Bahnaric-Vietnamese Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tran</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huong</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quynh</namePart>
<namePart type="family">Vo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phong</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tho</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rifki</namePart>
<namePart type="given">Afina</namePart>
<namePart type="family">Putri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelina</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanmi</namePart>
<namePart type="family">Koyejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-242-8</identifier>
</relatedItem>
<abstract>The Bahnar people, one of Vietnam’s ethnic minorities, represent an underserved community with limited access to modern technologies. Developing an effective Bahnaric-Vietnamese translation system is essential for fostering linguistic exchange, preserving cultural heritage, and empowering local communities by bridging communication barriers. With advancements in Artificial Intelligence (AI), Neural Machine Translation (NMT) has achieved remarkable success across various language pairs. However, the low-resource nature of Bahnaric, characterized by data scarcity, vocabulary constraints, and the lack of parallel corpora, poses significant challenges to building an accurate and efficient translation system. To address these challenges, we propose a novel hybrid architecture for Bahnaric-Vietnamese translation, with BARTBahnar as its core language model. BARTBahnar is developed by continually training a pre-trained Vietnamese model, BARTPho, on augmented monolingual Bahnaric data, followed by fine-tuning on bilingual datasets. This transfer learning approach reduces training costs while effectively capturing linguistic similarities between the two languages. Additionally, we implement advanced data augmentation techniques to enrich and diversify training data, further enhancing BARTBahnar’s robustness and translation accuracy. Beyond leveraging the language model, our hybrid system integrates rule-based and statistical methods to improve translation quality. Experimental results show substantial improvements on bilingual Bahnaric-Vietnamese datasets, validating the effectiveness of our approach for low-resource translation. To support further research, we open-source our code and related materials at https://github.com/ura-hcmut/BARTBahnar.</abstract>
<identifier type="citekey">nguyen-etal-2025-serving</identifier>
<identifier type="doi">10.18653/v1/2025.lm4uc-1.5</identifier>
<location>
<url>https://aclanthology.org/2025.lm4uc-1.5/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>32</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Serving the Underserved: Leveraging BARTBahnar Language Model for Bahnaric-Vietnamese Translation
%A Nguyen, Long
%A Le, Tran
%A Nguyen, Huong
%A Vo, Quynh
%A Nguyen, Phong
%A Quan, Tho
%Y Truong, Sang
%Y Putri, Rifki Afina
%Y Nguyen, Duc
%Y Wang, Angelina
%Y Ho, Daniel
%Y Oh, Alice
%Y Koyejo, Sanmi
%S Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-242-8
%F nguyen-etal-2025-serving
%X The Bahnar people, one of Vietnam’s ethnic minorities, represent an underserved community with limited access to modern technologies. Developing an effective Bahnaric-Vietnamese translation system is essential for fostering linguistic exchange, preserving cultural heritage, and empowering local communities by bridging communication barriers. With advancements in Artificial Intelligence (AI), Neural Machine Translation (NMT) has achieved remarkable success across various language pairs. However, the low-resource nature of Bahnaric, characterized by data scarcity, vocabulary constraints, and the lack of parallel corpora, poses significant challenges to building an accurate and efficient translation system. To address these challenges, we propose a novel hybrid architecture for Bahnaric-Vietnamese translation, with BARTBahnar as its core language model. BARTBahnar is developed by continually training a pre-trained Vietnamese model, BARTPho, on augmented monolingual Bahnaric data, followed by fine-tuning on bilingual datasets. This transfer learning approach reduces training costs while effectively capturing linguistic similarities between the two languages. Additionally, we implement advanced data augmentation techniques to enrich and diversify training data, further enhancing BARTBahnar’s robustness and translation accuracy. Beyond leveraging the language model, our hybrid system integrates rule-based and statistical methods to improve translation quality. Experimental results show substantial improvements on bilingual Bahnaric-Vietnamese datasets, validating the effectiveness of our approach for low-resource translation. To support further research, we open-source our code and related materials at https://github.com/ura-hcmut/BARTBahnar.
%R 10.18653/v1/2025.lm4uc-1.5
%U https://aclanthology.org/2025.lm4uc-1.5/
%U https://doi.org/10.18653/v1/2025.lm4uc-1.5
%P 32-41
Markdown (Informal)
[Serving the Underserved: Leveraging BARTBahnar Language Model for Bahnaric-Vietnamese Translation](https://aclanthology.org/2025.lm4uc-1.5/) (Nguyen et al., LM4UC 2025)
ACL