<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kulik-etal-2026-precision">
    <titleInfo>
        <title>Precision over Scale: A Polish–Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Grzegorz</namePart>
        <namePart type="family">Kulik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikołaj</namePart>
        <namePart type="family">Pokrywka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Jatowt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wojciech</namePart>
        <namePart type="family">Kusa</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Dialectal machine translation remains challenging due to limited data and strong linguistic variation not captured by standard benchmarks, which often assume standardized and well–edited text. We study Polish–Silesian MT using neural and rule–based systems, evaluating on SiLTT — a new Pol–Szl testset, alongside established BOUQuET and FLORES benchmarks. Results show our rule–based system is consistently strongest on SiLTT and BOUQuET datasets and that TranslateGemma fine–tuned on a curated dataset improves over strong neural baselines but does not surpass the rule–based system in dialectal settings. We release SiLTT and our best neural model to support further research.</abstract>
    <identifier type="citekey">kulik-etal-2026-precision</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2056/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>43783</start>
            <end>43792</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Precision over Scale: A Polish–Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models
%A Kulik, Grzegorz
%A Pokrywka, Mikołaj
%A Jatowt, Adam
%A Kusa, Wojciech
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kulik-etal-2026-precision
%X Dialectal machine translation remains challenging due to limited data and strong linguistic variation not captured by standard benchmarks, which often assume standardized and well–edited text. We study Polish–Silesian MT using neural and rule–based systems, evaluating on SiLTT — a new Pol–Szl testset, alongside established BOUQuET and FLORES benchmarks. Results show our rule–based system is consistently strongest on SiLTT and BOUQuET datasets and that TranslateGemma fine–tuned on a curated dataset improves over strong neural baselines but does not surpass the rule–based system in dialectal settings. We release SiLTT and our best neural model to support further research.
%U https://aclanthology.org/2026.findings-emnlp.2056/
%P 43783-43792

Markdown (Informal)

[Precision over Scale: A Polish–Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models](https://aclanthology.org/2026.findings-emnlp.2056/) (Kulik et al., Findings 2026)

• Precision over Scale: A Polish–Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models (Kulik et al., Findings 2026)

ACL

• Grzegorz Kulik, Mikołaj Pokrywka, Adam Jatowt, and Wojciech Kusa. 2026. Precision over Scale: A Polish–Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 43783–43792, Budapest, Hungary. Association for Computational Linguistics.