<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-zyc">
    <titleInfo>
        <title>ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sunny</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="family">Youner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dean</namePart>
        <namePart type="family">Cahill</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 investigate contextual embedding manipulation for Word Sense Disambiguation (WSD)as part of SemEval-2026 Task 5. We propose four approaches built on BERT-like pretrainedmodels, experimenting with the informativeness of similarity calculations and classificationmethods. We introduce scratch-trained cross-attention mechanisms inspired by GLiNER to compute similarity between definition or synonym representations and the full context. Our best performance achieved 57% accuracy with a Spearman correlation of 0.20. Our results suggest that finetuning strategy and trainng curriculum matter more than pretrained model choice for this novel task, and we identify several directions for future improvement. View our code base at: https://github.com/heliosraz/SemEval52026</abstract>
    <identifier type="citekey">zhou-etal-2026-zyc</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.371/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>2960</start>
            <end>2966</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD
%A Zhou, Sunny
%A Youner, Jordan
%A Cahill, Dean
%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 zhou-etal-2026-zyc
%X We investigate contextual embedding manipulation for Word Sense Disambiguation (WSD)as part of SemEval-2026 Task 5. We propose four approaches built on BERT-like pretrainedmodels, experimenting with the informativeness of similarity calculations and classificationmethods. We introduce scratch-trained cross-attention mechanisms inspired by GLiNER to compute similarity between definition or synonym representations and the full context. Our best performance achieved 57% accuracy with a Spearman correlation of 0.20. Our results suggest that finetuning strategy and trainng curriculum matter more than pretrained model choice for this novel task, and we identify several directions for future improvement. View our code base at: https://github.com/heliosraz/SemEval52026
%U https://aclanthology.org/2026.semeval-1.371/
%P 2960-2966

Markdown (Informal)

[ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD](https://aclanthology.org/2026.semeval-1.371/) (Zhou et al., SemEval 2026)

• ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD (Zhou et al., SemEval 2026)

ACL

• Sunny Zhou, Jordan Youner, and Dean Cahill. 2026. ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2960–2966, San Diego, California, USA. Association for Computational Linguistics.