@inproceedings{diab-etal-2016-creating,
title = "Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched {A}rabic Data",
author = "Diab, Mona and
Ghoneim, Mahmoud and
Hawwari, Abdelati and
AlGhamdi, Fahad and
AlMarwani, Nada and
Al-Badrashiny, Mohamed",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1669",
pages = "4228--4235",
abstract = "We present our effort to create a large Multi-Layered representational repository of Linguistic Code-Switched Arabic data. The process involves developing clear annotation standards and Guidelines, streamlining the annotation process, and implementing quality control measures. We used two main protocols for annotation: in-lab gold annotations and crowd sourcing annotations. We developed a web-based annotation tool to facilitate the management of the annotation process. The current version of the repository contains a total of 886,252 tokens that are tagged into one of sixteen code-switching tags. The data exhibits code switching between Modern Standard Arabic and Egyptian Dialectal Arabic representing three data genres: Tweets, commentaries, and discussion fora. The overall Inter-Annotator Agreement is 93.1{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diab-etal-2016-creating">
<titleInfo>
<title>Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched Arabic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Ghoneim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelati</namePart>
<namePart type="family">Hawwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">AlGhamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nada</namePart>
<namePart type="family">AlMarwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Al-Badrashiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our effort to create a large Multi-Layered representational repository of Linguistic Code-Switched Arabic data. The process involves developing clear annotation standards and Guidelines, streamlining the annotation process, and implementing quality control measures. We used two main protocols for annotation: in-lab gold annotations and crowd sourcing annotations. We developed a web-based annotation tool to facilitate the management of the annotation process. The current version of the repository contains a total of 886,252 tokens that are tagged into one of sixteen code-switching tags. The data exhibits code switching between Modern Standard Arabic and Egyptian Dialectal Arabic representing three data genres: Tweets, commentaries, and discussion fora. The overall Inter-Annotator Agreement is 93.1%.</abstract>
<identifier type="citekey">diab-etal-2016-creating</identifier>
<location>
<url>https://aclanthology.org/L16-1669</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4228</start>
<end>4235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched Arabic Data
%A Diab, Mona
%A Ghoneim, Mahmoud
%A Hawwari, Abdelati
%A AlGhamdi, Fahad
%A AlMarwani, Nada
%A Al-Badrashiny, Mohamed
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F diab-etal-2016-creating
%X We present our effort to create a large Multi-Layered representational repository of Linguistic Code-Switched Arabic data. The process involves developing clear annotation standards and Guidelines, streamlining the annotation process, and implementing quality control measures. We used two main protocols for annotation: in-lab gold annotations and crowd sourcing annotations. We developed a web-based annotation tool to facilitate the management of the annotation process. The current version of the repository contains a total of 886,252 tokens that are tagged into one of sixteen code-switching tags. The data exhibits code switching between Modern Standard Arabic and Egyptian Dialectal Arabic representing three data genres: Tweets, commentaries, and discussion fora. The overall Inter-Annotator Agreement is 93.1%.
%U https://aclanthology.org/L16-1669
%P 4228-4235
Markdown (Informal)
[Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched Arabic Data](https://aclanthology.org/L16-1669) (Diab et al., LREC 2016)
ACL