<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fesenko-etal-2026-mining">
    <titleInfo>
        <title>Mining Native Ukrainian Paraphrases: A Multi-Source Comparison</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vladyslav</namePart>
        <namePart type="family">Fesenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hanna</namePart>
        <namePart type="family">Dydyk-Meush</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Volodymyr</namePart>
        <namePart type="family">Mudryi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mariana</namePart>
            <namePart type="family">Romanyshyn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Lviv, Ukraine</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-359-3</identifier>
    </relatedItem>
    <abstract>We introduce a Ukrainian paraphrase dataset mined from event-aligned news headlines and compare it with translated and LLM-generated data sources. Candidate pairs are retrieved from native Ukrainian news titles and filtered using semantic and lexical constraints to form a training corpus in a semi-automatic pipeline. Human evaluation indicates that the sources differ in useful ways: LLM-generated paraphrases are generally stronger in meaning preservation, whereas news-mined pairs offer greater lexical variation while remaining fluent and meaning-preserving. We tune mT5-large and mT0-large and evaluate them on several held-out test sets, including a human-validated subset. Relative to Spivavtor-large, the models achieve comparable semantic preservation with lower copying on the combined and human-validated sets. Overall, the findings highlight the value of naturally mined Ukrainian paraphrases as supervision for low-resource paraphrase generation.</abstract>
    <identifier type="citekey">fesenko-etal-2026-mining</identifier>
    <location>
        <url>https://aclanthology.org/2026.unlp-1.17/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>199</start>
            <end>208</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mining Native Ukrainian Paraphrases: A Multi-Source Comparison
%A Fesenko, Vladyslav
%A Dydyk-Meush, Hanna
%A Mudryi, Volodymyr
%Y Romanyshyn, Mariana
%S Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026)
%D 2026
%8 May
%I Association for Computational Linguistics
%C Lviv, Ukraine
%@ 979-8-89176-359-3
%F fesenko-etal-2026-mining
%X We introduce a Ukrainian paraphrase dataset mined from event-aligned news headlines and compare it with translated and LLM-generated data sources. Candidate pairs are retrieved from native Ukrainian news titles and filtered using semantic and lexical constraints to form a training corpus in a semi-automatic pipeline. Human evaluation indicates that the sources differ in useful ways: LLM-generated paraphrases are generally stronger in meaning preservation, whereas news-mined pairs offer greater lexical variation while remaining fluent and meaning-preserving. We tune mT5-large and mT0-large and evaluate them on several held-out test sets, including a human-validated subset. Relative to Spivavtor-large, the models achieve comparable semantic preservation with lower copying on the combined and human-validated sets. Overall, the findings highlight the value of naturally mined Ukrainian paraphrases as supervision for low-resource paraphrase generation.
%U https://aclanthology.org/2026.unlp-1.17/
%P 199-208

Markdown (Informal)

[Mining Native Ukrainian Paraphrases: A Multi-Source Comparison](https://aclanthology.org/2026.unlp-1.17/) (Fesenko et al., UNLP 2026)

• Mining Native Ukrainian Paraphrases: A Multi-Source Comparison (Fesenko et al., UNLP 2026)

ACL

• Vladyslav Fesenko, Hanna Dydyk-Meush, and Volodymyr Mudryi. 2026. Mining Native Ukrainian Paraphrases: A Multi-Source Comparison. In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), pages 199–208, Lviv, Ukraine. Association for Computational Linguistics.