<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="au-2026-solosemantics">
    <titleInfo>
        <title>SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Steven</namePart>
        <namePart type="family">Au</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>This paper describes Team SoloSemantics’ submissions to SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning. We began with lightweight neuro-symbolic knowledge-graph baselines, but a triplet-tuned MPNet bi-encoder produced stronger semantic separation in our experiments. We adopted a shared dense encoder family across both tracks and kept the KG and fusion variants as diagnostic baselines. Team SoloSemantics ranked 22nd on Track A and 9th on Track B. Our reproducibility audit further shows that the KG branch was often too sparse on short summaries to represent abstract narrative relations reliably under the current extraction pipeline.</abstract>
    <identifier type="citekey">au-2026-solosemantics</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.201/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1547</start>
            <end>1553</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity
%A Au, Steven
%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 au-2026-solosemantics
%X This paper describes Team SoloSemantics’ submissions to SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning. We began with lightweight neuro-symbolic knowledge-graph baselines, but a triplet-tuned MPNet bi-encoder produced stronger semantic separation in our experiments. We adopted a shared dense encoder family across both tracks and kept the KG and fusion variants as diagnostic baselines. Team SoloSemantics ranked 22nd on Track A and 9th on Track B. Our reproducibility audit further shows that the KG branch was often too sparse on short summaries to represent abstract narrative relations reliably under the current extraction pipeline.
%U https://aclanthology.org/2026.semeval-1.201/
%P 1547-1553

Markdown (Informal)

[SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity](https://aclanthology.org/2026.semeval-1.201/) (Au, SemEval 2026)

• SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity (Au, SemEval 2026)

ACL

• Steven Au. 2026. SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1547–1553, San Diego, California, USA. Association for Computational Linguistics.