@inproceedings{grigorian-umishov-2026-expanding,
title = "Expanding {C}hechen Machine Translation Resources: {SMOL}, {BOUQ}u{ET}, and {WMT}24++ Extensions",
author = "Grigorian, Vladislav and
Umishov, Abu-Viskhan",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.195/",
pages = "2505--2509",
ISBN = "979-8-89176-474-3",
abstract = "We introduce a new fork of the SMOL training dataset along with forks of the BOUQuET and WMT24++ translation benchmarks for the Chechen language. We train a model on SMOL and calculate BLEU and chrF++ scores on the introduced benchmarks to evaluate how training on such a limited amount of data may contribute to the model{'}s Chechen-Russian translation capability. The introduced resources provide a unified evaluation framework for Chechen machine translation and allow measuring the transfer of improvements across different benchmark datasets. Our experiments establish baseline results for future research on Chechen translation and demonstrate the potential of utilizing small-scale parallel corpora for improving low-resource language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grigorian-umishov-2026-expanding">
<titleInfo>
<title>Expanding Chechen Machine Translation Resources: SMOL, BOUQuET, and WMT24++ Extensions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Grigorian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abu-Viskhan</namePart>
<namePart type="family">Umishov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>We introduce a new fork of the SMOL training dataset along with forks of the BOUQuET and WMT24++ translation benchmarks for the Chechen language. We train a model on SMOL and calculate BLEU and chrF++ scores on the introduced benchmarks to evaluate how training on such a limited amount of data may contribute to the model’s Chechen-Russian translation capability. The introduced resources provide a unified evaluation framework for Chechen machine translation and allow measuring the transfer of improvements across different benchmark datasets. Our experiments establish baseline results for future research on Chechen translation and demonstrate the potential of utilizing small-scale parallel corpora for improving low-resource language models.</abstract>
<identifier type="citekey">grigorian-umishov-2026-expanding</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.195/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2505</start>
<end>2509</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Expanding Chechen Machine Translation Resources: SMOL, BOUQuET, and WMT24++ Extensions
%A Grigorian, Vladislav
%A Umishov, Abu-Viskhan
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F grigorian-umishov-2026-expanding
%X We introduce a new fork of the SMOL training dataset along with forks of the BOUQuET and WMT24++ translation benchmarks for the Chechen language. We train a model on SMOL and calculate BLEU and chrF++ scores on the introduced benchmarks to evaluate how training on such a limited amount of data may contribute to the model’s Chechen-Russian translation capability. The introduced resources provide a unified evaluation framework for Chechen machine translation and allow measuring the transfer of improvements across different benchmark datasets. Our experiments establish baseline results for future research on Chechen translation and demonstrate the potential of utilizing small-scale parallel corpora for improving low-resource language models.
%U https://aclanthology.org/2026.wmt-main.195/
%P 2505-2509
Markdown (Informal)
[Expanding Chechen Machine Translation Resources: SMOL, BOUQuET, and WMT24++ Extensions](https://aclanthology.org/2026.wmt-main.195/) (Grigorian & Umishov, WMT 2026)
ACL