@inproceedings{d9739b0fb30a4acdb592e4fb7cbdfa50,
title = "The SAMER Arabic Text Simplification Corpus",
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.",
keywords = "Arabic, Readability, Text Simplification",
author = "Bashar Alhafni and Reem Hazim and Liberato, {Juan Pi{\~n}eros} and {Al Khalil}, Muhamed and Nizar Habash",
note = "Publisher Copyright: {\textcopyright} 2024 ELRA Language Resource Association: CC BY-NC 4.0.; Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 ; Conference date: 20-05-2024 Through 25-05-2024",
year = "2024",
language = "English (US)",
series = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "16079--16093",
editor = "Nicoletta Calzolari and Min-Yen Kan and Veronique Hoste and Alessandro Lenci and Sakriani Sakti and Nianwen Xue",
booktitle = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
}