<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volchek-poritski-2026-krosny">
    <titleInfo>
        <title>Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Oksana</namePart>
        <namePart type="family">Volchek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vladislav</namePart>
        <namePart type="family">Poritski</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>This paper describes our submission to the WMT26 General Machine Translation shared task for the English → Belarusian direction. In lower-resourced morphologically rich languages like Belarusian, open-weight large language models (LLMs) frequently struggle with orthographic fidelity, hallucinated vocabulary, and negative transfer from related high-resource languages. To address these issues, we implemented Krosny, an iterative, resource-augmented pipeline built on top of TranslateGemma 12B. The system translates each segment in three stages: (1) dictionary-augmented generation, (2) refinement using a reference grammatical database, and (3) rule-based post-processing followed by an LLM-as-a-judge candidate selection. We find a small but consistent improvement over the baseline TranslateGemma 12B. In comparison with other constrained-track systems of WMT26, the performance of Krosny is mid-tier. We release the source code of our implementation (https://github.com/volchek/Krosny-WMT26).</abstract>
    <identifier type="citekey">volchek-poritski-2026-krosny</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.80/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1425</start>
            <end>1429</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation
%A Volchek, Oksana
%A Poritski, Vladislav
%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 volchek-poritski-2026-krosny
%X This paper describes our submission to the WMT26 General Machine Translation shared task for the English → Belarusian direction. In lower-resourced morphologically rich languages like Belarusian, open-weight large language models (LLMs) frequently struggle with orthographic fidelity, hallucinated vocabulary, and negative transfer from related high-resource languages. To address these issues, we implemented Krosny, an iterative, resource-augmented pipeline built on top of TranslateGemma 12B. The system translates each segment in three stages: (1) dictionary-augmented generation, (2) refinement using a reference grammatical database, and (3) rule-based post-processing followed by an LLM-as-a-judge candidate selection. We find a small but consistent improvement over the baseline TranslateGemma 12B. In comparison with other constrained-track systems of WMT26, the performance of Krosny is mid-tier. We release the source code of our implementation (https://github.com/volchek/Krosny-WMT26).
%U https://aclanthology.org/2026.wmt-main.80/
%P 1425-1429

Markdown (Informal)

[Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation](https://aclanthology.org/2026.wmt-main.80/) (Volchek & Poritski, WMT 2026)

• Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation (Volchek & Poritski, WMT 2026)

ACL

• Oksana Volchek and Vladislav Poritski. 2026. Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1425–1429, Budapest, Hungary. Association for Computational Linguistics.