Towards compact and efficient Slovak summarization models

Sebastian Petrik; Giang Nguyen

doi:10.18653/v1/2025.bsnlp-1.7

Towards compact and efficient Slovak summarization models

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Language models, especially LLMs, often face significant limitations due to their high resource demands. While various model compression methods have emerged, their application to smaller models in multilingual and low-resource settings remains understudied. Our work evaluates selected decoder and embedding pruning methods on T5-based models for abstractive summarization in English and Slovak using a parallel dataset. The results reveal differences in model performance degradation and expand the limited Slovak summarization resources and models.

Anthology ID:: 2025.bsnlp-1.7
Volume:: Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Jakub Piskorski, Pavel Přibáň, Preslav Nakov, Roman Yangarber, Michal Marcinczuk
Venues:: BSNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 58–68
Language:
URL:: https://aclanthology.org/2025.bsnlp-1.7/
DOI:: 10.18653/v1/2025.bsnlp-1.7
Bibkey:
Cite (ACL):: Sebastian Petrik and Giang Nguyen. 2025. Towards compact and efficient Slovak summarization models. In Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025), pages 58–68, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Towards compact and efficient Slovak summarization models (Petrik & Nguyen, BSNLP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.bsnlp-1.7.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{petrik-nguyen-2025-towards,
    title = "Towards compact and efficient {S}lovak summarization models",
    author = "Petrik, Sebastian  and
      Nguyen, Giang",
    editor = "Piskorski, Jakub  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Nakov, Preslav  and
      Yangarber, Roman  and
      Marcinczuk, Michal",
    booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.bsnlp-1.7/",
    doi = "10.18653/v1/2025.bsnlp-1.7",
    pages = "58--68",
    ISBN = "978-1-959429-57-9",
    abstract = "Language models, especially LLMs, often face significant limitations due to their high resource demands. While various model compression methods have emerged, their application to smaller models in multilingual and low-resource settings remains understudied. Our work evaluates selected decoder and embedding pruning methods on T5-based models for abstractive summarization in English and Slovak using a parallel dataset. The results reveal differences in model performance degradation and expand the limited Slovak summarization resources and models."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrik-nguyen-2025-towards">
    <titleInfo>
        <title>Towards compact and efficient Slovak summarization models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Petrik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Giang</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jakub</namePart>
            <namePart type="family">Piskorski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pavel</namePart>
            <namePart type="family">Přibáň</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Roman</namePart>
            <namePart type="family">Yangarber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michal</namePart>
            <namePart type="family">Marcinczuk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">978-1-959429-57-9</identifier>
    </relatedItem>
    <abstract>Language models, especially LLMs, often face significant limitations due to their high resource demands. While various model compression methods have emerged, their application to smaller models in multilingual and low-resource settings remains understudied. Our work evaluates selected decoder and embedding pruning methods on T5-based models for abstractive summarization in English and Slovak using a parallel dataset. The results reveal differences in model performance degradation and expand the limited Slovak summarization resources and models.</abstract>
    <identifier type="citekey">petrik-nguyen-2025-towards</identifier>
    <identifier type="doi">10.18653/v1/2025.bsnlp-1.7</identifier>
    <location>
        <url>https://aclanthology.org/2025.bsnlp-1.7/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>58</start>
            <end>68</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Towards compact and efficient Slovak summarization models
%A Petrik, Sebastian
%A Nguyen, Giang
%Y Piskorski, Jakub
%Y Přibáň, Pavel
%Y Nakov, Preslav
%Y Yangarber, Roman
%Y Marcinczuk, Michal
%S Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-57-9
%F petrik-nguyen-2025-towards
%X Language models, especially LLMs, often face significant limitations due to their high resource demands. While various model compression methods have emerged, their application to smaller models in multilingual and low-resource settings remains understudied. Our work evaluates selected decoder and embedding pruning methods on T5-based models for abstractive summarization in English and Slovak using a parallel dataset. The results reveal differences in model performance degradation and expand the limited Slovak summarization resources and models.
%R 10.18653/v1/2025.bsnlp-1.7
%U https://aclanthology.org/2025.bsnlp-1.7/
%U https://doi.org/10.18653/v1/2025.bsnlp-1.7
%P 58-68

Download as File

Markdown (Informal)

[Towards compact and efficient Slovak summarization models](https://aclanthology.org/2025.bsnlp-1.7/) (Petrik & Nguyen, BSNLP 2025)

Towards compact and efficient Slovak summarization models (Petrik & Nguyen, BSNLP 2025)

ACL

Sebastian Petrik and Giang Nguyen. 2025. Towards compact and efficient Slovak summarization models. In Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025), pages 58–68, Vienna, Austria. Association for Computational Linguistics.