@inproceedings{metinov-2026-ensemble,
title = "Ensemble Methods for Low-Resource {R}ussian-{K}yrgyz Machine Translation: When Diverse Models Beat Better Models",
author = "Metinov, Adilet",
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-1.24/",
pages = "235--237",
ISBN = "979-8-89176-366-1",
abstract = "We present our submission to the LoResMT 2026 Shared Task on Russian-Kyrgyz machine translation. Our approach demonstrates that ensembling diverse translation models with simple consensus-based voting can significantly outperform individual models, achieving a +1.37 CHRF++ improvement over our best single model. Notably, we find that including ``weaker'' models in the ensemble improves overall performance, challenging the conventional assumption that ensembles should only combine top-performing systems. Our system achieved 49.31 CHRF++ on the public leaderboard and 48.55 CHRF++ on the final private test set, placing 3rd in the Russian-Kyrgyz track using only open-weight models without any fine-tuning on parallel Kyrgyz data. We report several counter-intuitive findings: (1) simple voting outperforms quality-weighted selection, (2) more diverse models help even when individually weaker, and (3) post-processing ``corrections'' can hurt performance when reference translations contain similar artifacts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="metinov-2026-ensemble">
<titleInfo>
<title>Ensemble Methods for Low-Resource Russian-Kyrgyz Machine Translation: When Diverse Models Beat Better Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adilet</namePart>
<namePart type="family">Metinov</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>We present our submission to the LoResMT 2026 Shared Task on Russian-Kyrgyz machine translation. Our approach demonstrates that ensembling diverse translation models with simple consensus-based voting can significantly outperform individual models, achieving a +1.37 CHRF++ improvement over our best single model. Notably, we find that including “weaker” models in the ensemble improves overall performance, challenging the conventional assumption that ensembles should only combine top-performing systems. Our system achieved 49.31 CHRF++ on the public leaderboard and 48.55 CHRF++ on the final private test set, placing 3rd in the Russian-Kyrgyz track using only open-weight models without any fine-tuning on parallel Kyrgyz data. We report several counter-intuitive findings: (1) simple voting outperforms quality-weighted selection, (2) more diverse models help even when individually weaker, and (3) post-processing “corrections” can hurt performance when reference translations contain similar artifacts.</abstract>
<identifier type="citekey">metinov-2026-ensemble</identifier>
<location>
<url>https://aclanthology.org/2026.loresmt-1.24/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>235</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ensemble Methods for Low-Resource Russian-Kyrgyz Machine Translation: When Diverse Models Beat Better Models
%A Metinov, Adilet
%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 metinov-2026-ensemble
%X We present our submission to the LoResMT 2026 Shared Task on Russian-Kyrgyz machine translation. Our approach demonstrates that ensembling diverse translation models with simple consensus-based voting can significantly outperform individual models, achieving a +1.37 CHRF++ improvement over our best single model. Notably, we find that including “weaker” models in the ensemble improves overall performance, challenging the conventional assumption that ensembles should only combine top-performing systems. Our system achieved 49.31 CHRF++ on the public leaderboard and 48.55 CHRF++ on the final private test set, placing 3rd in the Russian-Kyrgyz track using only open-weight models without any fine-tuning on parallel Kyrgyz data. We report several counter-intuitive findings: (1) simple voting outperforms quality-weighted selection, (2) more diverse models help even when individually weaker, and (3) post-processing “corrections” can hurt performance when reference translations contain similar artifacts.
%U https://aclanthology.org/2026.loresmt-1.24/
%P 235-237
Markdown (Informal)
[Ensemble Methods for Low-Resource Russian-Kyrgyz Machine Translation: When Diverse Models Beat Better Models](https://aclanthology.org/2026.loresmt-1.24/) (Metinov, LoResMT 2026)
ACL