@inproceedings{zagar-etal-2024-senta-sentence,
title = "{SENTA}: Sentence Simplification System for {S}lovene",
author = "{\v{Z}}agar, Ale{\v{s}} and
Klemen, Matej and
Robnik-{\v{S}}ikonja, Marko and
Kosem, Iztok",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1279",
pages = "14687--14692",
abstract = "Ensuring universal access to written content, regardless of users{'} language proficiency and cognitive abilities, is of paramount importance. Sentence simplification, which involves converting complex sentences into more accessible forms while preserving their meaning, plays a crucial role in enhancing text accessibility. This paper introduces SENTA, a system for sentence simplification in Slovene. The system consists of two components. First, a neural classifier identifies sentences that require simplification, and second, a large Slovene language model based on T5 architecture is fine-tuned to transform complex texts into a simpler form, achieving an excellent SARI score of 41. Both automatic and qualitative evaluations provide important insights into the problem, highlighting areas for future research in multilingual applications, and fluency maintenance. Finally, SENTA is integrated into a freely accessible, user-friendly user interface, offering a valuable service to less-fluent Slovene users.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zagar-etal-2024-senta-sentence">
<titleInfo>
<title>SENTA: Sentence Simplification System for Slovene</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleš</namePart>
<namePart type="family">Žagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matej</namePart>
<namePart type="family">Klemen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Robnik-Šikonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iztok</namePart>
<namePart type="family">Kosem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ensuring universal access to written content, regardless of users’ language proficiency and cognitive abilities, is of paramount importance. Sentence simplification, which involves converting complex sentences into more accessible forms while preserving their meaning, plays a crucial role in enhancing text accessibility. This paper introduces SENTA, a system for sentence simplification in Slovene. The system consists of two components. First, a neural classifier identifies sentences that require simplification, and second, a large Slovene language model based on T5 architecture is fine-tuned to transform complex texts into a simpler form, achieving an excellent SARI score of 41. Both automatic and qualitative evaluations provide important insights into the problem, highlighting areas for future research in multilingual applications, and fluency maintenance. Finally, SENTA is integrated into a freely accessible, user-friendly user interface, offering a valuable service to less-fluent Slovene users.</abstract>
<identifier type="citekey">zagar-etal-2024-senta-sentence</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1279</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14687</start>
<end>14692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SENTA: Sentence Simplification System for Slovene
%A Žagar, Aleš
%A Klemen, Matej
%A Robnik-Šikonja, Marko
%A Kosem, Iztok
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zagar-etal-2024-senta-sentence
%X Ensuring universal access to written content, regardless of users’ language proficiency and cognitive abilities, is of paramount importance. Sentence simplification, which involves converting complex sentences into more accessible forms while preserving their meaning, plays a crucial role in enhancing text accessibility. This paper introduces SENTA, a system for sentence simplification in Slovene. The system consists of two components. First, a neural classifier identifies sentences that require simplification, and second, a large Slovene language model based on T5 architecture is fine-tuned to transform complex texts into a simpler form, achieving an excellent SARI score of 41. Both automatic and qualitative evaluations provide important insights into the problem, highlighting areas for future research in multilingual applications, and fluency maintenance. Finally, SENTA is integrated into a freely accessible, user-friendly user interface, offering a valuable service to less-fluent Slovene users.
%U https://aclanthology.org/2024.lrec-main.1279
%P 14687-14692
Markdown (Informal)
[SENTA: Sentence Simplification System for Slovene](https://aclanthology.org/2024.lrec-main.1279) (Žagar et al., LREC-COLING 2024)
ACL
- Aleš Žagar, Matej Klemen, Marko Robnik-Šikonja, and Iztok Kosem. 2024. SENTA: Sentence Simplification System for Slovene. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14687–14692, Torino, Italia. ELRA and ICCL.