<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bevers-etal-2026-duluth">
    <titleInfo>
        <title>Duluth at SemEval-2026 Task 4: A Hybrid Approach to Narrative Similarity using Bi-Encoder Embeddings with Cross-Encoder Tie breaking using Learned Weights</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maxwell</namePart>
        <namePart type="family">Bevers</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aidan</namePart>
        <namePart type="family">Carlson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ted</namePart>
        <namePart type="family">Pedersen</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>We present a hybrid system for SemEval-2026 Task 4 on Narrative Similarity. Our approach decomposes the stories into four narrative components: theme, plot, emotion, and outcome. Each component is then encoded using a biencoder (all-mpnet-base-v2), and cosine similarities are combined through a learned pairwise ranking model. When similarity scores between candidate stories fall within a small margin of error, a cross-encoder (ms-marcoMiniLM-L-6-v2) is used as a tie-breaker. Our final system achieves 58.5% accuracy on the official test set, placing us at 39th overall. Error analysis reveals that the system struggles with complex themes, multiple protagonists, and contrasting outcomes.</abstract>
    <identifier type="citekey">bevers-etal-2026-duluth</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.127/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>927</start>
            <end>931</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Duluth at SemEval-2026 Task 4: A Hybrid Approach to Narrative Similarity using Bi-Encoder Embeddings with Cross-Encoder Tie breaking using Learned Weights
%A Bevers, Maxwell
%A Carlson, Aidan
%A Pedersen, Ted
%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 bevers-etal-2026-duluth
%X We present a hybrid system for SemEval-2026 Task 4 on Narrative Similarity. Our approach decomposes the stories into four narrative components: theme, plot, emotion, and outcome. Each component is then encoded using a biencoder (all-mpnet-base-v2), and cosine similarities are combined through a learned pairwise ranking model. When similarity scores between candidate stories fall within a small margin of error, a cross-encoder (ms-marcoMiniLM-L-6-v2) is used as a tie-breaker. Our final system achieves 58.5% accuracy on the official test set, placing us at 39th overall. Error analysis reveals that the system struggles with complex themes, multiple protagonists, and contrasting outcomes.
%U https://aclanthology.org/2026.semeval-1.127/
%P 927-931

Markdown (Informal)

[Duluth at SemEval-2026 Task 4: A Hybrid Approach to Narrative Similarity using Bi-Encoder Embeddings with Cross-Encoder Tie breaking using Learned Weights](https://aclanthology.org/2026.semeval-1.127/) (Bevers et al., SemEval 2026)

• Duluth at SemEval-2026 Task 4: A Hybrid Approach to Narrative Similarity using Bi-Encoder Embeddings with Cross-Encoder Tie breaking using Learned Weights (Bevers et al., SemEval 2026)

ACL

• Maxwell Bevers, Aidan Carlson, and Ted Pedersen. 2026. Duluth at SemEval-2026 Task 4: A Hybrid Approach to Narrative Similarity using Bi-Encoder Embeddings with Cross-Encoder Tie breaking using Learned Weights. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 927–931, San Diego, California, USA. Association for Computational Linguistics.