@inproceedings{07371d8c6f534c51949032c52d4c48bd,
title = "Building a Corpus for Palestinian Arabic: a Preliminary Study",
abstract = "This paper presents preliminary results in building an annotated corpus of the Palestinian Arabic dialect. The corpus consists of about 43K words, stemming from diverse resources. The paper discusses some linguistic facts about the Palestinian dialect, compared with the Modern Standard Arabic, especially in terms of morphological, orthographic, and lexical variations, and suggests some directions to resolve the challenges these differences pose to the annotation goal. Furthermore, we present two pilot studies that investigate whether existing tools for processing Modern Standard Arabic and Egyptian Arabic can be used to speed up the annotation process of our Palestinian Arabic corpus.",
author = "Mustafa Jarrar and Nizar Habash and Diyam Akra and Nasser Zalmout",
note = "Publisher Copyright: {\textcopyright}2014 Association for Computational Linguistics; EMNLP 2014 Workshop on Arabic Natural Language Processing, ANLP 2014 ; Conference date: 25-10-2014",
year = "2014",
month = oct,
day = "25",
language = "English",
series = "ANLP 2014 - EMNLP 2014 Workshop on Arabic Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "18--27",
editor = "Nizar Habash and Stephan Vogel",
booktitle = "ANLP 2014 - EMNLP 2014 Workshop on Arabic Natural Language Processing, Proceedings",
address = "United States",
}