<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khaidukova-etal-2026-narrative">
    <titleInfo>
        <title>Narrative Team at SemEval-2026 Task 4: Two-Stage Contrastive Learning for Narrative Similarity Assessment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tatiana</namePart>
        <namePart type="family">Khaidukova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ana</namePart>
        <namePart type="family">Ciobanu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniela</namePart>
        <namePart type="family">Gifu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Diana</namePart>
        <namePart type="family">Trandabat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>For SemEval-2026 Task 4, we introduce a unified two-stage framework based on a RoBERTa-large encoder. Stage 1 performs contrastive pre-training on synthetic triplets to learn general narrative similarity patterns. Stage 2 fine-tunes the model with a ranking-based objective tailored to Track A.The resulting encoder supports both binary similarity classification (Track A) and narrative embedding generation (Track B) without architectural changes. Our system achieves an accuracy of 0.64 on Track A and 0.69 on Track B, outperforming single-stage baselines and demonstrating that combining synthetic contrastive supervision with task-specific ranking yields stable and reusable narrative representations.</abstract>
    <identifier type="citekey">khaidukova-etal-2026-narrative</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.22/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>146</start>
            <end>152</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Narrative Team at SemEval-2026 Task 4: Two-Stage Contrastive Learning for Narrative Similarity Assessment
%A Khaidukova, Tatiana
%A Ciobanu, Ana
%A Gifu, Daniela
%A Trandabat, Diana
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F khaidukova-etal-2026-narrative
%X For SemEval-2026 Task 4, we introduce a unified two-stage framework based on a RoBERTa-large encoder. Stage 1 performs contrastive pre-training on synthetic triplets to learn general narrative similarity patterns. Stage 2 fine-tunes the model with a ranking-based objective tailored to Track A.The resulting encoder supports both binary similarity classification (Track A) and narrative embedding generation (Track B) without architectural changes. Our system achieves an accuracy of 0.64 on Track A and 0.69 on Track B, outperforming single-stage baselines and demonstrating that combining synthetic contrastive supervision with task-specific ranking yields stable and reusable narrative representations.
%U https://aclanthology.org/2026.semeval-1.22/
%P 146-152

Markdown (Informal)

[Narrative Team at SemEval-2026 Task 4: Two-Stage Contrastive Learning for Narrative Similarity Assessment](https://aclanthology.org/2026.semeval-1.22/) (Khaidukova et al., SemEval 2026)

• Narrative Team at SemEval-2026 Task 4: Two-Stage Contrastive Learning for Narrative Similarity Assessment (Khaidukova et al., SemEval 2026)

ACL

• Tatiana Khaidukova, Ana Ciobanu, Daniela Gifu, and Diana Trandabat. 2026. Narrative Team at SemEval-2026 Task 4: Two-Stage Contrastive Learning for Narrative Similarity Assessment. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 146–152, San Diego, California, USA. Association for Computational Linguistics.