@inproceedings{233ab4f49bdf44a499ab761f39674cea,
title = "A morphologically annotated corpus of Emirati Arabic",
abstract = "We present an ongoing effort on the first large-scale morphologically manually annotated corpus of Emirati Arabic. This corpus includes about 200,000 words selected from eight Gumar corpus novels in the Emirati Arabic variety. The selected texts are being annotated for tokenization, part-of-speech, lemmatization, English glosses and dialect identification. The orthography of the text is also adjusted for errors and inconsistencies. We discuss the guidelines for each part of the annotation components, and the annotation interface we use. We report on the quality of the annotation through an inter-annotator agreement measure.",
keywords = "Annotation, Gulf Arabic, Morphology, Part-of-Speech Tagging",
author = "Salam Khalifa and Nizar Habash and Fadhl Eryani and Ossama Obeid and Dana Abdulrahim and Kaabi, {Meera Al}",
note = "Publisher Copyright: {\textcopyright} LREC 2018 - 11th International Conference on Language Resources and Evaluation. All rights reserved.; 11th International Conference on Language Resources and Evaluation, LREC 2018 ; Conference date: 07-05-2018 Through 12-05-2018",
year = "2019",
language = "English",
series = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
publisher = "European Language Resources Association (ELRA)",
pages = "3839--3846",
editor = "Hitoshi Isahara and Bente Maegaard and Stelios Piperidis and Christopher Cieri and Thierry Declerck and Koiti Hasida and Helene Mazo and Khalid Choukri and Sara Goggi and Joseph Mariani and Asuncion Moreno and Nicoletta Calzolari and Jan Odijk and Takenobu Tokunaga",
booktitle = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
}