@inproceedings{eryani-habash-2021-automatic,
title = "Automatic {R}omanization of {A}rabic Bibliographic Records",
author = "Eryani, Fadhl and
Habash, Nizar",
editor = "Habash, Nizar and
Bouamor, Houda and
Hajj, Hazem and
Magdy, Walid and
Zaghouani, Wajdi and
Bougares, Fethi and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Touileb, Samia",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.23",
pages = "213--218",
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 \textit{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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eryani-habash-2021-automatic">
<titleInfo>
<title>Automatic Romanization of Arabic Bibliographic Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fadhl</namePart>
<namePart type="family">Eryani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">eryani-habash-2021-automatic</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.23</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>213</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Romanization of Arabic Bibliographic Records
%A Eryani, Fadhl
%A Habash, Nizar
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Hajj, Hazem
%Y Magdy, Walid
%Y Zaghouani, Wajdi
%Y Bougares, Fethi
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F eryani-habash-2021-automatic
%X 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.
%U https://aclanthology.org/2021.wanlp-1.23
%P 213-218
Markdown (Informal)
[Automatic Romanization of Arabic Bibliographic Records](https://aclanthology.org/2021.wanlp-1.23) (Eryani & Habash, WANLP 2021)
ACL