<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jorgensen-breitung-2025-margins">
    <titleInfo>
        <title>Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tollef</namePart>
        <namePart type="given">Emil</namePart>
        <namePart type="family">Jørgensen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jens</namePart>
        <namePart type="family">Breitung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="family">Johansson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Stymne</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>University of Tartu Library</publisher>
            <place>
                <placeTerm type="text">Tallinn, Estonia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">978-9908-53-109-0</identifier>
    </relatedItem>
    <abstract>This paper explores retrieval with sentence embeddings by fine-tuning sentence-transformer models for classification while preserving their ability to capture semantic similarity. To evaluate this balance, we introduce two opposing metrics – polarity score and semantic similarity score – that measure the model’s capacity to separate classes and retain semantic relationships between sentences. We propose a system that augments supervised datasets with contrastive pairs and triplets, training models under various configurations and evaluating their performance on top-k sentence retrieval. Experiments on two binary classification tasks demonstrate that reducing the margin parameter of loss functions greatly mitigates the trade-off between the metrics. These findings suggest that a single fine-tuned model can effectively handle joint classification and retrieval tasks, particularly in low-resource settings, without relying on multiple specialized models.</abstract>
    <identifier type="citekey">jorgensen-breitung-2025-margins</identifier>
    <location>
        <url>https://aclanthology.org/2025.nodalida-1.28/</url>
    </location>
    <part>
        <date>2025-03</date>
        <extent unit="page">
            <start>269</start>
            <end>278</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings
%A Jørgensen, Tollef Emil
%A Breitung, Jens
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F jorgensen-breitung-2025-margins
%X This paper explores retrieval with sentence embeddings by fine-tuning sentence-transformer models for classification while preserving their ability to capture semantic similarity. To evaluate this balance, we introduce two opposing metrics – polarity score and semantic similarity score – that measure the model’s capacity to separate classes and retain semantic relationships between sentences. We propose a system that augments supervised datasets with contrastive pairs and triplets, training models under various configurations and evaluating their performance on top-k sentence retrieval. Experiments on two binary classification tasks demonstrate that reducing the margin parameter of loss functions greatly mitigates the trade-off between the metrics. These findings suggest that a single fine-tuned model can effectively handle joint classification and retrieval tasks, particularly in low-resource settings, without relying on multiple specialized models.
%U https://aclanthology.org/2025.nodalida-1.28/
%P 269-278

Markdown (Informal)

[Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings](https://aclanthology.org/2025.nodalida-1.28/) (Jørgensen & Breitung, NoDaLiDa 2025)

• Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings (Jørgensen & Breitung, NoDaLiDa 2025)

ACL

• Tollef Emil Jørgensen and Jens Breitung. 2025. Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 269–278, Tallinn, Estonia. University of Tartu Library.