@inproceedings{tyurin-2026-devlake,
title = "{D}ev{L}ake at {L}o{R}es{MT} 2026: The Impact of Pre-training and Model Scale on {R}ussian-{B}ashkir Low-Resource Translation",
author = "Tyurin, Vyacheslav",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Washington, Jonathan and
Oco, Nathaniel and
Zhao, Xiaobing",
booktitle = "Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages ({L}o{R}es{MT} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loresmt-1.18/",
pages = "209--212",
ISBN = "979-8-89176-366-1",
abstract = "This paper describes the submission of Team DevLake for the LoResMT 2026 Shared Task on Russian-Bashkir machine translation. We conducted a comprehensive comparative study of three distinct neural architectures: NLLB-200 (1.3B), M2M-100 (418M), and MarianMT (77M). To overcome hardware constraints, we employed parameter-efficient fine-tuning techniques (QLoRA) and extensive data filtering using a domain-specific BERT-based classifier. Our experiments demonstrate that the presence of the target language (Bashkir) in the model{'}s pre-training data is the decisive factor for performance. Our best system, a fine-tuned NLLB-200-1.3B model augmented with exact match retrieval, achieved a CHRF++ score of 52.67. We also report on negative results with custom tokenization for smaller models, providing insights into the limitations of vocabulary adaptation without extensive pre-training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tyurin-2026-devlake">
<titleInfo>
<title>DevLake at LoResMT 2026: The Impact of Pre-training and Model Scale on Russian-Bashkir Low-Resource Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vyacheslav</namePart>
<namePart type="family">Tyurin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-366-1</identifier>
</relatedItem>
<abstract>This paper describes the submission of Team DevLake for the LoResMT 2026 Shared Task on Russian-Bashkir machine translation. We conducted a comprehensive comparative study of three distinct neural architectures: NLLB-200 (1.3B), M2M-100 (418M), and MarianMT (77M). To overcome hardware constraints, we employed parameter-efficient fine-tuning techniques (QLoRA) and extensive data filtering using a domain-specific BERT-based classifier. Our experiments demonstrate that the presence of the target language (Bashkir) in the model’s pre-training data is the decisive factor for performance. Our best system, a fine-tuned NLLB-200-1.3B model augmented with exact match retrieval, achieved a CHRF++ score of 52.67. We also report on negative results with custom tokenization for smaller models, providing insights into the limitations of vocabulary adaptation without extensive pre-training.</abstract>
<identifier type="citekey">tyurin-2026-devlake</identifier>
<location>
<url>https://aclanthology.org/2026.loresmt-1.18/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>209</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DevLake at LoResMT 2026: The Impact of Pre-training and Model Scale on Russian-Bashkir Low-Resource Translation
%A Tyurin, Vyacheslav
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-366-1
%F tyurin-2026-devlake
%X This paper describes the submission of Team DevLake for the LoResMT 2026 Shared Task on Russian-Bashkir machine translation. We conducted a comprehensive comparative study of three distinct neural architectures: NLLB-200 (1.3B), M2M-100 (418M), and MarianMT (77M). To overcome hardware constraints, we employed parameter-efficient fine-tuning techniques (QLoRA) and extensive data filtering using a domain-specific BERT-based classifier. Our experiments demonstrate that the presence of the target language (Bashkir) in the model’s pre-training data is the decisive factor for performance. Our best system, a fine-tuned NLLB-200-1.3B model augmented with exact match retrieval, achieved a CHRF++ score of 52.67. We also report on negative results with custom tokenization for smaller models, providing insights into the limitations of vocabulary adaptation without extensive pre-training.
%U https://aclanthology.org/2026.loresmt-1.18/
%P 209-212
Markdown (Informal)
[DevLake at LoResMT 2026: The Impact of Pre-training and Model Scale on Russian-Bashkir Low-Resource Translation](https://aclanthology.org/2026.loresmt-1.18/) (Tyurin, LoResMT 2026)
ACL