@inproceedings{alhafni-etal-2024-samer,
title = "The {SAMER} {A}rabic Text Simplification Corpus",
author = "Alhafni, Bashar and
Hazim, Reem and
Pineros Liberato, Juan David and
Al Khalil, Muhamed and
Habash, Nizar",
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.1398/",
pages = "16079--16093",
abstract = "We present the SAMER Corpus, the first manually annotated Arabic parallel corpus for text simplification targeting school-aged learners. Our corpus comprises texts of 159K words selected from 15 publicly available Arabic fiction novels most of which were published between 1865 and 1955. Our corpus includes readability level annotations at both the document and word levels, as well as two simplified parallel versions for each text targeting learners at two different readability levels. We describe the corpus selection process, and outline the guidelines we followed to create the annotations and ensure their quality. Our corpus is publicly available to support and encourage research on Arabic text simplification, Arabic automatic readability assessment, and the development of Arabic pedagogical language technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alhafni-etal-2024-samer">
<titleInfo>
<title>The SAMER Arabic Text Simplification Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Hazim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Pineros Liberato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhamed</namePart>
<namePart type="family">Al Khalil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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>We present the SAMER Corpus, the first manually annotated Arabic parallel corpus for text simplification targeting school-aged learners. Our corpus comprises texts of 159K words selected from 15 publicly available Arabic fiction novels most of which were published between 1865 and 1955. Our corpus includes readability level annotations at both the document and word levels, as well as two simplified parallel versions for each text targeting learners at two different readability levels. We describe the corpus selection process, and outline the guidelines we followed to create the annotations and ensure their quality. Our corpus is publicly available to support and encourage research on Arabic text simplification, Arabic automatic readability assessment, and the development of Arabic pedagogical language technologies.</abstract>
<identifier type="citekey">alhafni-etal-2024-samer</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1398/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16079</start>
<end>16093</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The SAMER Arabic Text Simplification Corpus
%A Alhafni, Bashar
%A Hazim, Reem
%A Pineros Liberato, Juan David
%A Al Khalil, Muhamed
%A Habash, Nizar
%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 alhafni-etal-2024-samer
%X We present the SAMER Corpus, the first manually annotated Arabic parallel corpus for text simplification targeting school-aged learners. Our corpus comprises texts of 159K words selected from 15 publicly available Arabic fiction novels most of which were published between 1865 and 1955. Our corpus includes readability level annotations at both the document and word levels, as well as two simplified parallel versions for each text targeting learners at two different readability levels. We describe the corpus selection process, and outline the guidelines we followed to create the annotations and ensure their quality. Our corpus is publicly available to support and encourage research on Arabic text simplification, Arabic automatic readability assessment, and the development of Arabic pedagogical language technologies.
%U https://aclanthology.org/2024.lrec-main.1398/
%P 16079-16093
Markdown (Informal)
[The SAMER Arabic Text Simplification Corpus](https://aclanthology.org/2024.lrec-main.1398/) (Alhafni et al., LREC-COLING 2024)
ACL
- Bashar Alhafni, Reem Hazim, Juan David Pineros Liberato, Muhamed Al Khalil, and Nizar Habash. 2024. The SAMER Arabic Text Simplification Corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16079–16093, Torino, Italia. ELRA and ICCL.