@inproceedings{96049283426f4a5a8109476f5232413a,
title = "Arabic Diacritization: Stats, Rules, and Hacks",
abstract = "In this paper, we present a new and fast state-of-the-art Arabic diacritizer that guesses the diacritics of words and then their case endings. We employ a Viterbi decoder at word-level with back-off to stem, morphological patterns, and transliteration and sequence labeling based diacritization of named entities. For case endings, we use Support Vector Machine (SVM) based ranking coupled with morphological patterns and linguistic rules to properly guess case endings. We achieve a low word level diacritization error of 3.29\% and 12.77\% without and with case endings respectively on a new multi-genre free of copyright test set. We are making the diacritizer available for free for research purposes.",
author = "Kareem Darwish and Hamdy Mubarak and Ahmed Abdelali",
note = "Publisher Copyright: {\textcopyright}2017 Association for Computational Linguistics; 3rd Arabic Natural Language Processing Workshop, WANLP 2017 held at EACL 2017 ; Conference date: 03-04-2017",
year = "2017",
doi = "10.18653/v1/W17-1302",
language = "English",
series = "WANLP 2017, co-located with EACL 2017 - 3rd Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "9--17",
booktitle = "WANLP 2017, co-located with EACL 2017 - 3rd Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
address = "United States",
}