@inproceedings{dee9ebbecdd240d5a11d73c2f5afc449,
title = "Large scale Arabic error annotation: Guidelines and framework",
abstract = "We present annotation guidelines and a web-based annotation framework developed as part of an effort to create a manually annotated Arabic corpus of errors and corrections for various text types. Such a corpus will be invaluable for developing Arabic error correction tools, both for training models and as a gold standard for evaluating error correction algorithms. We summarize the guidelines we created. We also describe issues encountered during the training of the annotators, as well as problems that are specific to the Arabic language that arose during the annotation process. Finally, we present the annotation tool that was developed as part of this project, the annotation pipeline, and the quality of the resulting annotations.",
keywords = "Arabic, Error annotation, Guidelines",
author = "Wajdi Zaghouani and Behrang Mohit and Nizar Habash and Ossama Obeid and Nadi Tomeh and Alla Rozovskaya and Noura Farra and Sarah Alkuhlani and Kemal Oflazer",
note = "Funding Information: We thank anonymous reviewers for their valuable comments and suggestions. We also thank all our dedicated annotators: Hoda Fathy, Dhoha Abid, Mariem Fekih, Anissa Jrad, Hoda Ibrahim, Noor Alzeer, Samah Lakhal, Jihene Wefi, Elsherif Mahmoud and Hossam El-Husseini. We thank Al Jazeera News (and especially, Khalid Judia) for providing the user comments portion of our corpus. This publication was made possible by grants NPRP-4-1058-1-168 and YSREP-1-018-1-004 from the Qatar National Research Fund (a member of the Qatar Foundation). The statements made herein are solely the responsibility of the authors.; 9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
year = "2014",
language = "English (US)",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "2362--2369",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
}