@inproceedings{nezda-etal-2006-world,
title = "What in the world is a Shahab?: Wide Coverage Named Entity Recognition for {A}rabic",
author = "Nezda, Luke and
Hickl, Andrew and
Lehmann, John and
Fayyaz, Sarmad",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/368_pdf.pdf",
abstract = "This paper describes the development of CiceroArabic, the first wide coverage named entity recognition (NER) system for Modern Standard Arabic. Capable of classifying 18 different named entity classes with over 85{\%} F, CiceroArabic utilizes a new 800,000-word annotated Arabic newswire corpus in order to achieve high performance without the need for hand-crafted rules or morphological information. In addition to describing results from our system, we show that accurate named entity annotation for a large number of semantic classes is feasible, even for very large corpora, and we discuss new techniques designed to boost agreement and consistency among annotators over a long-term annotation effort.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nezda-etal-2006-world">
<titleInfo>
<title>What in the world is a Shahab?: Wide Coverage Named Entity Recognition for Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Nezda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Hickl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Lehmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarmad</namePart>
<namePart type="family">Fayyaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Gangemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the development of CiceroArabic, the first wide coverage named entity recognition (NER) system for Modern Standard Arabic. Capable of classifying 18 different named entity classes with over 85% F, CiceroArabic utilizes a new 800,000-word annotated Arabic newswire corpus in order to achieve high performance without the need for hand-crafted rules or morphological information. In addition to describing results from our system, we show that accurate named entity annotation for a large number of semantic classes is feasible, even for very large corpora, and we discuss new techniques designed to boost agreement and consistency among annotators over a long-term annotation effort.</abstract>
<identifier type="citekey">nezda-etal-2006-world</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/368_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What in the world is a Shahab?: Wide Coverage Named Entity Recognition for Arabic
%A Nezda, Luke
%A Hickl, Andrew
%A Lehmann, John
%A Fayyaz, Sarmad
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F nezda-etal-2006-world
%X This paper describes the development of CiceroArabic, the first wide coverage named entity recognition (NER) system for Modern Standard Arabic. Capable of classifying 18 different named entity classes with over 85% F, CiceroArabic utilizes a new 800,000-word annotated Arabic newswire corpus in order to achieve high performance without the need for hand-crafted rules or morphological information. In addition to describing results from our system, we show that accurate named entity annotation for a large number of semantic classes is feasible, even for very large corpora, and we discuss new techniques designed to boost agreement and consistency among annotators over a long-term annotation effort.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/368_pdf.pdf
Markdown (Informal)
[What in the world is a Shahab?: Wide Coverage Named Entity Recognition for Arabic](http://www.lrec-conf.org/proceedings/lrec2006/pdf/368_pdf.pdf) (Nezda et al., LREC 2006)
ACL