@inproceedings{abuhakema-etal-2008-annotating,
title = "Annotating an {A}rabic Learner Corpus for Error",
author = "Abuhakema, Ghazi and
Faraj, Reem and
Feldman, Anna and
Fitzpatrick, Eileen",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/343_paper.pdf",
abstract = "This paper describes an ongoing project in which we are collecting a learner corpus of Arabic, developing a tagset for error annotation and performing Computer-aided Error Analysis (CEA) on the data. We adapted the French Interlanguage Database FRIDA tagset (Granger, 2003a) to the data. We chose FRIDA in order to follow a known standard and to see whether the changes needed to move from a French to an Arabic tagset would give us a measure of the distance between the two languages with respect to learner difficulty. The current collection of texts, which is constantly growing, contains intermediate and advanced-level student writings. We describe the need for such corpora, the learner data we have collected and the tagset we have developed. We also describe the error frequency distribution of both proficiency levels and the ongoing work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abuhakema-etal-2008-annotating">
<titleInfo>
<title>Annotating an Arabic Learner Corpus for Error</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ghazi</namePart>
<namePart type="family">Abuhakema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Faraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eileen</namePart>
<namePart type="family">Fitzpatrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an ongoing project in which we are collecting a learner corpus of Arabic, developing a tagset for error annotation and performing Computer-aided Error Analysis (CEA) on the data. We adapted the French Interlanguage Database FRIDA tagset (Granger, 2003a) to the data. We chose FRIDA in order to follow a known standard and to see whether the changes needed to move from a French to an Arabic tagset would give us a measure of the distance between the two languages with respect to learner difficulty. The current collection of texts, which is constantly growing, contains intermediate and advanced-level student writings. We describe the need for such corpora, the learner data we have collected and the tagset we have developed. We also describe the error frequency distribution of both proficiency levels and the ongoing work.</abstract>
<identifier type="citekey">abuhakema-etal-2008-annotating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/343_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating an Arabic Learner Corpus for Error
%A Abuhakema, Ghazi
%A Faraj, Reem
%A Feldman, Anna
%A Fitzpatrick, Eileen
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F abuhakema-etal-2008-annotating
%X This paper describes an ongoing project in which we are collecting a learner corpus of Arabic, developing a tagset for error annotation and performing Computer-aided Error Analysis (CEA) on the data. We adapted the French Interlanguage Database FRIDA tagset (Granger, 2003a) to the data. We chose FRIDA in order to follow a known standard and to see whether the changes needed to move from a French to an Arabic tagset would give us a measure of the distance between the two languages with respect to learner difficulty. The current collection of texts, which is constantly growing, contains intermediate and advanced-level student writings. We describe the need for such corpora, the learner data we have collected and the tagset we have developed. We also describe the error frequency distribution of both proficiency levels and the ongoing work.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/343_paper.pdf
Markdown (Informal)
[Annotating an Arabic Learner Corpus for Error](http://www.lrec-conf.org/proceedings/lrec2008/pdf/343_paper.pdf) (Abuhakema et al., LREC 2008)
ACL
- Ghazi Abuhakema, Reem Faraj, Anna Feldman, and Eileen Fitzpatrick. 2008. Annotating an Arabic Learner Corpus for Error. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).