<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chellaf-el-hammoud-etal-2026-using">
    <titleInfo>
        <title>Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chaimae</namePart>
        <namePart type="family">Chellaf El Hammoud</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Salima</namePart>
        <namePart type="family">Mdhaffar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yannick</namePart>
        <namePart type="family">Estève</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stéphane</namePart>
        <namePart type="family">Huet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Abstractive summarization aims to generate concise summaries by creating new sentences, allowing for flexible rephrasing. However, this approach can be vulnerable to inaccuracies, particularly ‘hallucinations’ where the model introduces non-existent information. In this paper, we leverage the use of multimodal and multilingual sentence embeddings derived from pre-trained models such as LaBSE, SONAR, and BGE-M3, and feed them into a modified BART-based French model. A Named Entity Injection mechanism that appends tokenized named entities to the decoder input is introduced, in order to improve the factual consistency of the generated summary. Our novel framework, SBARThez, is applicable to both text and speech inputs and supports cross-lingual summarization; it shows competitive performance relative to token-level baselines, especially for low-resource languages, while generating more concise and abstract summaries.</abstract>
    <identifier type="citekey">chellaf-el-hammoud-etal-2026-using</identifier>
    <identifier type="doi">10.63317/59f6s77tynig</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.774/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>9873</start>
            <end>9883</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization
%A Chellaf El Hammoud, Chaimae
%A Mdhaffar, Salima
%A Estève, Yannick
%A Huet, Stéphane
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F chellaf-el-hammoud-etal-2026-using
%X Abstractive summarization aims to generate concise summaries by creating new sentences, allowing for flexible rephrasing. However, this approach can be vulnerable to inaccuracies, particularly ‘hallucinations’ where the model introduces non-existent information. In this paper, we leverage the use of multimodal and multilingual sentence embeddings derived from pre-trained models such as LaBSE, SONAR, and BGE-M3, and feed them into a modified BART-based French model. A Named Entity Injection mechanism that appends tokenized named entities to the decoder input is introduced, in order to improve the factual consistency of the generated summary. Our novel framework, SBARThez, is applicable to both text and speech inputs and supports cross-lingual summarization; it shows competitive performance relative to token-level baselines, especially for low-resource languages, while generating more concise and abstract summaries.
%R 10.63317/59f6s77tynig
%U https://aclanthology.org/2026.lrec-1.774/
%U https://doi.org/10.63317/59f6s77tynig
%P 9873-9883

Markdown (Informal)

[Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization](https://aclanthology.org/2026.lrec-1.774/) (Chellaf El Hammoud et al., LREC 2026)

• Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization (Chellaf El Hammoud et al., LREC 2026)

ACL

• Chaimae Chellaf El Hammoud, Salima Mdhaffar, Yannick Estève, and Stéphane Huet. 2026. Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9873–9883, Palma de Mallorca, Spain. ELRA Language Resource Association.