@inproceedings{jamelot-etal-2024-improving-text,
title = "Improving Text Readability through Segmentation into Rheses",
author = "Jamelot, Antoine and
Quiniou, Solen and
Hamon, Sophie",
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.781",
pages = "8925--8930",
abstract = "Enhancing text readability is crucial for readers with challenges like dyslexia. This paper delves into the segmentation of sentences into rheses, i.e. rhythmic and semantic units. Their aim is to clarify sentence structures for improved comprehension, through a harmonious balance between syntactic accuracy, the natural rhythm of reading aloud, and the delineation of meaningful units. This study relates and compares our various attempts to improve a pre-existing rhesis segmentation tool, which is based on the selection of candidate segmentations. We also release TeRheSe (Texts with Rhesis Segmentation), a bilingual dataset, segmented into rheses, comprising 12 books from classic literature in French and English. We evaluated our approaches on this dataset, showing the efficiency of a novel approach based on token classification, reaching a F1-score of 90.0{\%} in English (previously 85.3{\%}) and 91.3{\%} in French (previously 88.0{\%}). We also study the potential of leveraging prosodic elements, though its definitive impact remains inconclusive.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jamelot-etal-2024-improving-text">
<titleInfo>
<title>Improving Text Readability through Segmentation into Rheses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Jamelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solen</namePart>
<namePart type="family">Quiniou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Hamon</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>Enhancing text readability is crucial for readers with challenges like dyslexia. This paper delves into the segmentation of sentences into rheses, i.e. rhythmic and semantic units. Their aim is to clarify sentence structures for improved comprehension, through a harmonious balance between syntactic accuracy, the natural rhythm of reading aloud, and the delineation of meaningful units. This study relates and compares our various attempts to improve a pre-existing rhesis segmentation tool, which is based on the selection of candidate segmentations. We also release TeRheSe (Texts with Rhesis Segmentation), a bilingual dataset, segmented into rheses, comprising 12 books from classic literature in French and English. We evaluated our approaches on this dataset, showing the efficiency of a novel approach based on token classification, reaching a F1-score of 90.0% in English (previously 85.3%) and 91.3% in French (previously 88.0%). We also study the potential of leveraging prosodic elements, though its definitive impact remains inconclusive.</abstract>
<identifier type="citekey">jamelot-etal-2024-improving-text</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.781</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8925</start>
<end>8930</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Text Readability through Segmentation into Rheses
%A Jamelot, Antoine
%A Quiniou, Solen
%A Hamon, Sophie
%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 jamelot-etal-2024-improving-text
%X Enhancing text readability is crucial for readers with challenges like dyslexia. This paper delves into the segmentation of sentences into rheses, i.e. rhythmic and semantic units. Their aim is to clarify sentence structures for improved comprehension, through a harmonious balance between syntactic accuracy, the natural rhythm of reading aloud, and the delineation of meaningful units. This study relates and compares our various attempts to improve a pre-existing rhesis segmentation tool, which is based on the selection of candidate segmentations. We also release TeRheSe (Texts with Rhesis Segmentation), a bilingual dataset, segmented into rheses, comprising 12 books from classic literature in French and English. We evaluated our approaches on this dataset, showing the efficiency of a novel approach based on token classification, reaching a F1-score of 90.0% in English (previously 85.3%) and 91.3% in French (previously 88.0%). We also study the potential of leveraging prosodic elements, though its definitive impact remains inconclusive.
%U https://aclanthology.org/2024.lrec-main.781
%P 8925-8930
Markdown (Informal)
[Improving Text Readability through Segmentation into Rheses](https://aclanthology.org/2024.lrec-main.781) (Jamelot et al., LREC-COLING 2024)
ACL
- Antoine Jamelot, Solen Quiniou, and Sophie Hamon. 2024. Improving Text Readability through Segmentation into Rheses. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8925–8930, Torino, Italia. ELRA and ICCL.