@inproceedings{zaghouani-dukes-2014-crowdsourcing,
title = "Can Crowdsourcing be used for Effective Annotation of {A}rabic?",
author = "Zaghouani, Wajdi and
Dukes, Kais",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/431_Paper.pdf",
pages = "224--228",
abstract = "Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Amazon Mechanical Turk (AMT) in order to assess the feasibility of using AMT workers (also known as Turkers) to perform linguistic annotation of Arabic. We used a gold standard data set taken from the Quran corpus project annotated with part-of-speech and morphological information. An Arabic language qualification test was used to filter out potential non-qualified participants. Two experiments were performed, a part-of-speech tagging task in where the annotators were asked to choose a correct word-category from a multiple choice list and case ending identification task. The results obtained so far showed that annotating Arabic grammatical case is harder than POS tagging, and crowdsourcing for Arabic linguistic annotation requiring expert annotators could be not as effective as other crowdsourcing experiments requiring less expertise and qualifications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-dukes-2014-crowdsourcing">
<titleInfo>
<title>Can Crowdsourcing be used for Effective Annotation of Arabic?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kais</namePart>
<namePart type="family">Dukes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Amazon Mechanical Turk (AMT) in order to assess the feasibility of using AMT workers (also known as Turkers) to perform linguistic annotation of Arabic. We used a gold standard data set taken from the Quran corpus project annotated with part-of-speech and morphological information. An Arabic language qualification test was used to filter out potential non-qualified participants. Two experiments were performed, a part-of-speech tagging task in where the annotators were asked to choose a correct word-category from a multiple choice list and case ending identification task. The results obtained so far showed that annotating Arabic grammatical case is harder than POS tagging, and crowdsourcing for Arabic linguistic annotation requiring expert annotators could be not as effective as other crowdsourcing experiments requiring less expertise and qualifications.</abstract>
<identifier type="citekey">zaghouani-dukes-2014-crowdsourcing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/431_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>224</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Crowdsourcing be used for Effective Annotation of Arabic?
%A Zaghouani, Wajdi
%A Dukes, Kais
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F zaghouani-dukes-2014-crowdsourcing
%X Crowdsourcing has been used recently as an alternative to traditional costly annotation by many natural language processing groups. In this paper, we explore the use of Amazon Mechanical Turk (AMT) in order to assess the feasibility of using AMT workers (also known as Turkers) to perform linguistic annotation of Arabic. We used a gold standard data set taken from the Quran corpus project annotated with part-of-speech and morphological information. An Arabic language qualification test was used to filter out potential non-qualified participants. Two experiments were performed, a part-of-speech tagging task in where the annotators were asked to choose a correct word-category from a multiple choice list and case ending identification task. The results obtained so far showed that annotating Arabic grammatical case is harder than POS tagging, and crowdsourcing for Arabic linguistic annotation requiring expert annotators could be not as effective as other crowdsourcing experiments requiring less expertise and qualifications.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/431_Paper.pdf
%P 224-228
Markdown (Informal)
[Can Crowdsourcing be used for Effective Annotation of Arabic?](http://www.lrec-conf.org/proceedings/lrec2014/pdf/431_Paper.pdf) (Zaghouani & Dukes, LREC 2014)
ACL