@inproceedings{f1b47907bebc412aa5bb8f7b914c9514,
title = "A large scale corpus of Gulf Arabic",
abstract = "Most Arabic natural language processing tools and resources are developed to serve Modern Standard Arabic (MSA), which is the official written language in the Arab World. Some Dialectal Arabic varieties, notably Egyptian Arabic, have received some attention lately and have a growing collection of resources that include annotated corpora and morphological analyzers and taggers. Gulf Arabic, however, lags behind in that respect. In this paper, we present the Gumar Corpus, a large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels. We annotate the corpus for sub-dialect information at the document level. We also present results of a preliminary study in the morphological annotation of Gulf Arabic which includes developing guidelines for a conventional orthography. The text of the corpus is publicly browsable through a web interface we developed for it.",
keywords = "Arabic dialects, Corpus, Gulf Arabic, Large-scale",
author = "Salam Khalifa and Nizar Habash and Dana Abdulrahim and Sara Hassan",
year = "2016",
language = "English (US)",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "4282--4289",
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",
}