@inproceedings{e51150d93452414bafcb1a6fab4cfb3d,
title = "Processing spontaneous orthography",
abstract = "In cases in which there is no standard orthography for a language or language variant, written texts will display a variety of orthographic choices. This is problematic for natural language processing (NLP) because it creates spurious data sparseness. We study the transformation of spontaneously spelled Egyptian Arabic into a conventionalized orthography which we have previously proposed for NLP purposes. We show that a two-stage process can reduce divergences from this standard by 69%, making subsequent processing of Egyptian Arabic easier.",
author = "Ramy Eskander and Nizar Habash and Owen Rambow and Nadi Tomeh",
year = "2013",
language = "English (US)",
series = "NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "585--595",
booktitle = "NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics",
note = "2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2013 ; Conference date: 09-06-2013 Through 14-06-2013",
}