@inproceedings{nguyen-etal-2026-bahnar,
title = "{B}ahnar{--}{V}ietnamese Parallel-Sentence Retrieval: A Low-Resource Case Study with Lexical, Neural, and Hybrid Methods",
author = "Nguyen, Thi Ty and
Nguyen, Long S. T. and
Tran-Truong, Phat T. and
Nguyen, Tan Sang and
Quan, Tho",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.59/",
pages = "1260--1280",
ISBN = "979-8-89176-439-2",
abstract = "For very low-resource language pairs such as Bahnar-Vietnamese, the relative effectiveness of generic multilingual, language-pair-specific lexical, and task-adapted retrieval remains unclear. We study Bahnar-Vietnamese parallel-sentence retrieval (bitext retrieval) as a controlled candidate-ranking task and compare lexical, alignment-based, neural, and hybrid methods under a development-based selection protocol. The strongest off-the-shelf encoder, LaBSE, reaches 24.24{\%} Recall@1, while symmetric IBM1 reaches 49.33{\%}. Among four in-domain modern dense retrievers, development selection chooses DPR-XM, which reaches 47.43{\%} Recall@1 and 72.21{\%} Recall@10. XLM-R LoRA reaches 64.02{\%} Recall@10, and the development-selected XLM-R-first IBM1 reranker gives the highest Recall@1 point estimate, at 51.62{\%}, with an MRR of 0.5579. Paired tests do not establish a significant difference between the hybrid and IBM1 at the 0.05 level, although reranking substantially improves over its neural first stage. Under pair-specific training, LoRA projection with CSLS also performs strongly on Khmer-Vietnamese and Lao-Vietnamese, reaching 80.14{\%} and 84.58{\%} Recall@1. Overall, the results show complementary strengths between lexical alignment and lightweight neural adaptation in low-resource bitext retrieval. Data and code are available at \url{https://github.com/NgThTy/translation-vn-bahna}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-bahnar">
<titleInfo>
<title>Bahnar–Vietnamese Parallel-Sentence Retrieval: A Low-Resource Case Study with Lexical, Neural, and Hybrid Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thi</namePart>
<namePart type="given">Ty</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="given">S</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phat</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Tran-Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tan</namePart>
<namePart type="given">Sang</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>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>For very low-resource language pairs such as Bahnar-Vietnamese, the relative effectiveness of generic multilingual, language-pair-specific lexical, and task-adapted retrieval remains unclear. We study Bahnar-Vietnamese parallel-sentence retrieval (bitext retrieval) as a controlled candidate-ranking task and compare lexical, alignment-based, neural, and hybrid methods under a development-based selection protocol. The strongest off-the-shelf encoder, LaBSE, reaches 24.24% Recall@1, while symmetric IBM1 reaches 49.33%. Among four in-domain modern dense retrievers, development selection chooses DPR-XM, which reaches 47.43% Recall@1 and 72.21% Recall@10. XLM-R LoRA reaches 64.02% Recall@10, and the development-selected XLM-R-first IBM1 reranker gives the highest Recall@1 point estimate, at 51.62%, with an MRR of 0.5579. Paired tests do not establish a significant difference between the hybrid and IBM1 at the 0.05 level, although reranking substantially improves over its neural first stage. Under pair-specific training, LoRA projection with CSLS also performs strongly on Khmer-Vietnamese and Lao-Vietnamese, reaching 80.14% and 84.58% Recall@1. Overall, the results show complementary strengths between lexical alignment and lightweight neural adaptation in low-resource bitext retrieval. Data and code are available at https://github.com/NgThTy/translation-vn-bahna.</abstract>
<identifier type="citekey">nguyen-etal-2026-bahnar</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.59/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1260</start>
<end>1280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bahnar–Vietnamese Parallel-Sentence Retrieval: A Low-Resource Case Study with Lexical, Neural, and Hybrid Methods
%A Nguyen, Thi Ty
%A Nguyen, Long S. T.
%A Tran-Truong, Phat T.
%A Nguyen, Tan Sang
%A Quan, Tho
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F nguyen-etal-2026-bahnar
%X For very low-resource language pairs such as Bahnar-Vietnamese, the relative effectiveness of generic multilingual, language-pair-specific lexical, and task-adapted retrieval remains unclear. We study Bahnar-Vietnamese parallel-sentence retrieval (bitext retrieval) as a controlled candidate-ranking task and compare lexical, alignment-based, neural, and hybrid methods under a development-based selection protocol. The strongest off-the-shelf encoder, LaBSE, reaches 24.24% Recall@1, while symmetric IBM1 reaches 49.33%. Among four in-domain modern dense retrievers, development selection chooses DPR-XM, which reaches 47.43% Recall@1 and 72.21% Recall@10. XLM-R LoRA reaches 64.02% Recall@10, and the development-selected XLM-R-first IBM1 reranker gives the highest Recall@1 point estimate, at 51.62%, with an MRR of 0.5579. Paired tests do not establish a significant difference between the hybrid and IBM1 at the 0.05 level, although reranking substantially improves over its neural first stage. Under pair-specific training, LoRA projection with CSLS also performs strongly on Khmer-Vietnamese and Lao-Vietnamese, reaching 80.14% and 84.58% Recall@1. Overall, the results show complementary strengths between lexical alignment and lightweight neural adaptation in low-resource bitext retrieval. Data and code are available at https://github.com/NgThTy/translation-vn-bahna.
%U https://aclanthology.org/2026.aacl-long.59/
%P 1260-1280
Markdown (Informal)
[Bahnar–Vietnamese Parallel-Sentence Retrieval: A Low-Resource Case Study with Lexical, Neural, and Hybrid Methods](https://aclanthology.org/2026.aacl-long.59/) (Nguyen et al., AACL-IJCNLP 2026)
ACL