@inproceedings{kay-rineer-2012-approaches,
title = "Approaches to {A}rabic Name Transliteration and Matching in the {D}ata{F}lux Quality Knowledge Base",
author = "Kay, Brant N. and
Rineer, Brian C.",
editor = "Farghaly, Ali and
Oroumchian, Farhad",
booktitle = "Fourth Workshop on Computational Approaches to Arabic-Script-based Languages",
month = nov # " 1",
year = "2012",
address = "San Diego, California, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2012.amta-caas14.5",
pages = "32--37",
abstract = "This paper discusses a hybrid approach to transliterating and matching Arabic names, as implemented in the DataFlux Quality Knowledge Base (QKB), a knowledge base used by data management software systems from SAS Institute, Inc. The approach to transliteration relies on a lexicon of names with their corresponding transliterations as its primary method, and falls back on PERL regular expression rules to transliterate any names that do not exist in the lexicon. Transliteration in the QKB is bi-directional; the technology transliterates Arabic names written in the Arabic script to the Latin script, and transliterates Arabic names written in the Latin script to Arabic. Arabic name matching takes a similar approach and relies on a lexicon of Arabic names and their corresponding transliterations, falling back on phonetic transliteration rules to transliterate names into the Latin script. All names are ultimately rendered in the Latin script before matching takes place. Thus, the technology is capable of matching names across the Arabic and Latin scripts, as well as within the Arabic script or within the Latin script. The goal of the authors of this paper was to build a software system capable of transliterating and matching Arabic names across scripts with an accuracy deemed to be acceptable according to internal software quality standards.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kay-rineer-2012-approaches">
<titleInfo>
<title>Approaches to Arabic Name Transliteration and Matching in the DataFlux Quality Knowledge Base</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brant</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Kay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Rineer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Fourth Workshop on Computational Approaches to Arabic-Script-based Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Farghaly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Oroumchian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses a hybrid approach to transliterating and matching Arabic names, as implemented in the DataFlux Quality Knowledge Base (QKB), a knowledge base used by data management software systems from SAS Institute, Inc. The approach to transliteration relies on a lexicon of names with their corresponding transliterations as its primary method, and falls back on PERL regular expression rules to transliterate any names that do not exist in the lexicon. Transliteration in the QKB is bi-directional; the technology transliterates Arabic names written in the Arabic script to the Latin script, and transliterates Arabic names written in the Latin script to Arabic. Arabic name matching takes a similar approach and relies on a lexicon of Arabic names and their corresponding transliterations, falling back on phonetic transliteration rules to transliterate names into the Latin script. All names are ultimately rendered in the Latin script before matching takes place. Thus, the technology is capable of matching names across the Arabic and Latin scripts, as well as within the Arabic script or within the Latin script. The goal of the authors of this paper was to build a software system capable of transliterating and matching Arabic names across scripts with an accuracy deemed to be acceptable according to internal software quality standards.</abstract>
<identifier type="citekey">kay-rineer-2012-approaches</identifier>
<location>
<url>https://aclanthology.org/2012.amta-caas14.5</url>
</location>
<part>
<date>2012-nov 1</date>
<extent unit="page">
<start>32</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Approaches to Arabic Name Transliteration and Matching in the DataFlux Quality Knowledge Base
%A Kay, Brant N.
%A Rineer, Brian C.
%Y Farghaly, Ali
%Y Oroumchian, Farhad
%S Fourth Workshop on Computational Approaches to Arabic-Script-based Languages
%D 2012
%8 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F kay-rineer-2012-approaches
%X This paper discusses a hybrid approach to transliterating and matching Arabic names, as implemented in the DataFlux Quality Knowledge Base (QKB), a knowledge base used by data management software systems from SAS Institute, Inc. The approach to transliteration relies on a lexicon of names with their corresponding transliterations as its primary method, and falls back on PERL regular expression rules to transliterate any names that do not exist in the lexicon. Transliteration in the QKB is bi-directional; the technology transliterates Arabic names written in the Arabic script to the Latin script, and transliterates Arabic names written in the Latin script to Arabic. Arabic name matching takes a similar approach and relies on a lexicon of Arabic names and their corresponding transliterations, falling back on phonetic transliteration rules to transliterate names into the Latin script. All names are ultimately rendered in the Latin script before matching takes place. Thus, the technology is capable of matching names across the Arabic and Latin scripts, as well as within the Arabic script or within the Latin script. The goal of the authors of this paper was to build a software system capable of transliterating and matching Arabic names across scripts with an accuracy deemed to be acceptable according to internal software quality standards.
%U https://aclanthology.org/2012.amta-caas14.5
%P 32-37
Markdown (Informal)
[Approaches to Arabic Name Transliteration and Matching in the DataFlux Quality Knowledge Base](https://aclanthology.org/2012.amta-caas14.5) (Kay & Rineer, AMTA 2012)
ACL