@inproceedings{eb52b7e121ec49c8b554ba6ebb892e2f,
title = "Automatic Romanization of Arabic Bibliographic Records",
abstract = "International library standards require cataloguers to tediously input Romanization of their catalogue records for the benefit of library users without specific language expertise. In this paper, we present the first reported results on the task of automatic Romanization of undiacritized Arabic bibliographic entries. This complex task requires the modeling of Arabic phonology, morphology, and even semantics. We collected a 2.5M word corpus of parallel Arabic and Romanized bibliographic entries, and benchmarked a number of models that vary in terms of complexity and resource dependence. Our best system reaches 89.3% exact word Romanization on a blind test set. We make our data and code publicly available.",
author = "Fadhl Eryani and Nizar Habash",
note = "Publisher Copyright: {\textcopyright} WANLP 2021 - 6th Arabic Natural Language Processing Workshop; 6th Arabic Natural Language Processing Workshop, WANLP 2021 ; Conference date: 19-04-2021",
year = "2021",
language = "English (US)",
series = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "213--218",
editor = "Nizar Habash and Houda Bouamor and Hazem Hajj and Walid Magdy and Wajdi Zaghouani and Fethi Bougares and Nadi Tomeh and Farha, {Ibrahim Abu} and Samia Touileb",
booktitle = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
}