@inproceedings{21d632435c5940abae16209bf3d8917a,
title = "Building an Arabic machine translation post-edited corpus: Guidelines and annotation",
abstract = "We present our guidelines and annotation procedure to create a human corrected machine translated post-edited corpus for the Modern Standard Arabic. Our overarching goal is to use the annotated corpus to develop automatic machine translation post-editing systems for Arabic that can be used to help accelerate the human revision process of translated texts. The creation of any manually annotated corpus usually presents many challenges. In order to address these challenges, we created comprehensive and simplified annotation guidelines which were used by a team of five annotators and one lead annotator. In order to ensure a high annotation agreement between the annotators, multiple training sessions were held and regular inter-annotator agreement measures were performed to check the annotation quality. The created corpus of manual post-edited translations of English to Arabic articles is the largest to date for this language pair.",
keywords = "Annotation, Guidelines, Post-editing",
author = "Wajdi Zaghouani and Nizar Habash and Ossama Obeid and Behrang Mohit and Houda Bouamor and Kemal Oflazer",
year = "2016",
language = "English",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "1869--1876",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Stelios Piperidis and Bente Maegaard and Joseph Mariani",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
note = "10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
}