@inproceedings{habash-palfreyman-2022-zaebuc,
title = "{ZAEBUC}: An Annotated {A}rabic-{E}nglish Bilingual Writer Corpus",
author = "Habash, Nizar and
Palfreyman, David",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.9",
pages = "79--88",
abstract = "We present ZAEBUC, an annotated Arabic-English bilingual writer corpus comprising short essays by first-year university students at Zayed University in the United Arab Emirates. We describe and discuss the various guidelines and pipeline processes we followed to create the annotations and quality check them. The annotations include spelling and grammar correction, morphological tokenization, Part-of-Speech tagging, lemmatization, and Common European Framework of Reference (CEFR) ratings. All of the annotations are done on Arabic and English texts using consistent guidelines as much as possible, with tracked alignments among the different annotations, and to the original raw texts. For morphological tokenization, POS tagging, and lemmatization, we use existing automatic annotation tools followed by manual correction. We also present various measurements and correlations with preliminary insights drawn from the data and annotations. The publicly available ZAEBUC corpus and its annotations are intended to be the stepping stones for additional annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="habash-palfreyman-2022-zaebuc">
<titleInfo>
<title>ZAEBUC: An Annotated Arabic-English Bilingual Writer Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Palfreyman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present ZAEBUC, an annotated Arabic-English bilingual writer corpus comprising short essays by first-year university students at Zayed University in the United Arab Emirates. We describe and discuss the various guidelines and pipeline processes we followed to create the annotations and quality check them. The annotations include spelling and grammar correction, morphological tokenization, Part-of-Speech tagging, lemmatization, and Common European Framework of Reference (CEFR) ratings. All of the annotations are done on Arabic and English texts using consistent guidelines as much as possible, with tracked alignments among the different annotations, and to the original raw texts. For morphological tokenization, POS tagging, and lemmatization, we use existing automatic annotation tools followed by manual correction. We also present various measurements and correlations with preliminary insights drawn from the data and annotations. The publicly available ZAEBUC corpus and its annotations are intended to be the stepping stones for additional annotations.</abstract>
<identifier type="citekey">habash-palfreyman-2022-zaebuc</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.9</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>79</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ZAEBUC: An Annotated Arabic-English Bilingual Writer Corpus
%A Habash, Nizar
%A Palfreyman, David
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F habash-palfreyman-2022-zaebuc
%X We present ZAEBUC, an annotated Arabic-English bilingual writer corpus comprising short essays by first-year university students at Zayed University in the United Arab Emirates. We describe and discuss the various guidelines and pipeline processes we followed to create the annotations and quality check them. The annotations include spelling and grammar correction, morphological tokenization, Part-of-Speech tagging, lemmatization, and Common European Framework of Reference (CEFR) ratings. All of the annotations are done on Arabic and English texts using consistent guidelines as much as possible, with tracked alignments among the different annotations, and to the original raw texts. For morphological tokenization, POS tagging, and lemmatization, we use existing automatic annotation tools followed by manual correction. We also present various measurements and correlations with preliminary insights drawn from the data and annotations. The publicly available ZAEBUC corpus and its annotations are intended to be the stepping stones for additional annotations.
%U https://aclanthology.org/2022.lrec-1.9
%P 79-88
Markdown (Informal)
[ZAEBUC: An Annotated Arabic-English Bilingual Writer Corpus](https://aclanthology.org/2022.lrec-1.9) (Habash & Palfreyman, LREC 2022)
ACL