@inproceedings{minh-etal-2025-challenge,
title = "Challenge Track: {JHARNA}-{MT}: A Copy-Augmented Hybrid of {L}o{RA}-Tuned {NLLB} and Lexical {SMT} with Minimum {B}ayes Risk Decoding for Low-Resource {I}ndic Languages",
author = "Minh, Dao Sy Duy and
Huynh, Trung Kiet and
Nguyen, Tran Chi and
Lam, Phu Quy Nguyen and
Pham, Phu-Hoa and
Dương, Nguyễn {\DJ}{\`i}nh H{\`a} and
Dinh, Dien and
Nguyen, Long HB",
editor = "Shukla, Ankita and
Kumar, Sandeep and
Bedi, Amrit Singh and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mmloso-1.13/",
pages = "114--120",
ISBN = "979-8-89176-311-1",
abstract = "This paper describes JHARNA-MT, our system for the MMLoSo 2025 Shared Task on translation between high-resource languages (Hindi, English) and four low-resource Indic tribal languages: Bhili, Gondi, Mundari, and Santali. The task poses significant challenges, including data sparsity, morphological richness, and structural divergence across language pairs. To address these, we propose a hybrid translation pipeline that integrates non-parametric retrieval, lexical statistical machine translation (SMT), and LoRA-tuned NLLB-200 neural machine translation under a unified Minimum Bayes Risk (MBR) decoding framework. Exact and fuzzy retrieval exploit redundancy in government and administrative texts, SMT with diagonal alignment priors and back-translation provides lexically faithful hypotheses, and the NLLB-LoRA component contributes fluent neural candidates. MBR decoding selects consensus translations using a metric-matched utility based on a weighted combination of BLEU and chrF, mitigating the complementary error modes of SMT and NMT. Our final system, further enhanced with script-aware digit normalization and entity-preserving post-processing, achieves a private leaderboard score of 186.37 and ranks 2nd overall in the shared task, with ablation studies confirming the contribution of each component."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="minh-etal-2025-challenge">
<titleInfo>
<title>Challenge Track: JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dao</namePart>
<namePart type="given">Sy</namePart>
<namePart type="given">Duy</namePart>
<namePart type="family">Minh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="given">Kiet</namePart>
<namePart type="family">Huynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tran</namePart>
<namePart type="given">Chi</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="given">Quy</namePart>
<namePart type="given">Nguyen</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu-Hoa</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyễn</namePart>
<namePart type="given">Đình</namePart>
<namePart type="given">Hà</namePart>
<namePart type="family">Dương</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>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="given">HB</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrit</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Bedi</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-311-1</identifier>
</relatedItem>
<abstract>This paper describes JHARNA-MT, our system for the MMLoSo 2025 Shared Task on translation between high-resource languages (Hindi, English) and four low-resource Indic tribal languages: Bhili, Gondi, Mundari, and Santali. The task poses significant challenges, including data sparsity, morphological richness, and structural divergence across language pairs. To address these, we propose a hybrid translation pipeline that integrates non-parametric retrieval, lexical statistical machine translation (SMT), and LoRA-tuned NLLB-200 neural machine translation under a unified Minimum Bayes Risk (MBR) decoding framework. Exact and fuzzy retrieval exploit redundancy in government and administrative texts, SMT with diagonal alignment priors and back-translation provides lexically faithful hypotheses, and the NLLB-LoRA component contributes fluent neural candidates. MBR decoding selects consensus translations using a metric-matched utility based on a weighted combination of BLEU and chrF, mitigating the complementary error modes of SMT and NMT. Our final system, further enhanced with script-aware digit normalization and entity-preserving post-processing, achieves a private leaderboard score of 186.37 and ranks 2nd overall in the shared task, with ablation studies confirming the contribution of each component.</abstract>
<identifier type="citekey">minh-etal-2025-challenge</identifier>
<location>
<url>https://aclanthology.org/2025.mmloso-1.13/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>114</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenge Track: JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages
%A Minh, Dao Sy Duy
%A Huynh, Trung Kiet
%A Nguyen, Tran Chi
%A Lam, Phu Quy Nguyen
%A Pham, Phu-Hoa
%A Dương, Nguyễn Đình Hà
%A Dinh, Dien
%A Nguyen, Long HB
%Y Shukla, Ankita
%Y Kumar, Sandeep
%Y Bedi, Amrit Singh
%Y Chakraborty, Tanmoy
%S Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-311-1
%F minh-etal-2025-challenge
%X This paper describes JHARNA-MT, our system for the MMLoSo 2025 Shared Task on translation between high-resource languages (Hindi, English) and four low-resource Indic tribal languages: Bhili, Gondi, Mundari, and Santali. The task poses significant challenges, including data sparsity, morphological richness, and structural divergence across language pairs. To address these, we propose a hybrid translation pipeline that integrates non-parametric retrieval, lexical statistical machine translation (SMT), and LoRA-tuned NLLB-200 neural machine translation under a unified Minimum Bayes Risk (MBR) decoding framework. Exact and fuzzy retrieval exploit redundancy in government and administrative texts, SMT with diagonal alignment priors and back-translation provides lexically faithful hypotheses, and the NLLB-LoRA component contributes fluent neural candidates. MBR decoding selects consensus translations using a metric-matched utility based on a weighted combination of BLEU and chrF, mitigating the complementary error modes of SMT and NMT. Our final system, further enhanced with script-aware digit normalization and entity-preserving post-processing, achieves a private leaderboard score of 186.37 and ranks 2nd overall in the shared task, with ablation studies confirming the contribution of each component.
%U https://aclanthology.org/2025.mmloso-1.13/
%P 114-120
Markdown (Informal)
[Challenge Track: JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages](https://aclanthology.org/2025.mmloso-1.13/) (Minh et al., MMLoSo 2025)
ACL
- Dao Sy Duy Minh, Trung Kiet Huynh, Tran Chi Nguyen, Phu Quy Nguyen Lam, Phu-Hoa Pham, Nguyễn Đình Hà Dương, Dien Dinh, and Long HB Nguyen. 2025. Challenge Track: JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages. In Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025), pages 114–120, Mumbai, India. Association for Computational Linguistics.