@inproceedings{brierley-etal-2012-open,
title = "Open-Source Boundary-Annotated Corpus for {A}rabic Speech and Language Processing",
author = "Brierley, Claire and
Sawalha, Majdi and
Atwell, Eric",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/240_Paper.pdf",
pages = "1011--1016",
abstract = "A boundary-annotated and part-of-speech tagged corpus is a prerequisite for developing phrase break classifiers. Boundary annotations in English speech corpora are descriptive, delimiting intonation units perceived by the listener. We take a novel approach to phrase break prediction for Arabic, deriving our prosodic annotation scheme from Tajw{\=\i}d (recitation) mark-up in the Qur'an which we then interpret as additional text-based data for computational analysis. This mark-up is prescriptive, and signifies a widely-used recitation style, and one of seven original styles of transmission. Here we report on version 1.0 of our Boundary-Annotated Qur'an dataset of 77430 words and 8230 sentences, where each word is tagged with prosodic and syntactic information at two coarse-grained levels. In (Sawalha et al., 2012), we use the dataset in phrase break prediction experiments. This research is part of a larger-scale project to produce annotation schemes, language resources, algorithms, and applications for Classical and Modern Standard Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brierley-etal-2012-open">
<titleInfo>
<title>Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Brierley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A boundary-annotated and part-of-speech tagged corpus is a prerequisite for developing phrase break classifiers. Boundary annotations in English speech corpora are descriptive, delimiting intonation units perceived by the listener. We take a novel approach to phrase break prediction for Arabic, deriving our prosodic annotation scheme from Tajwīd (recitation) mark-up in the Qur’an which we then interpret as additional text-based data for computational analysis. This mark-up is prescriptive, and signifies a widely-used recitation style, and one of seven original styles of transmission. Here we report on version 1.0 of our Boundary-Annotated Qur’an dataset of 77430 words and 8230 sentences, where each word is tagged with prosodic and syntactic information at two coarse-grained levels. In (Sawalha et al., 2012), we use the dataset in phrase break prediction experiments. This research is part of a larger-scale project to produce annotation schemes, language resources, algorithms, and applications for Classical and Modern Standard Arabic.</abstract>
<identifier type="citekey">brierley-etal-2012-open</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/240_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1011</start>
<end>1016</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing
%A Brierley, Claire
%A Sawalha, Majdi
%A Atwell, Eric
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F brierley-etal-2012-open
%X A boundary-annotated and part-of-speech tagged corpus is a prerequisite for developing phrase break classifiers. Boundary annotations in English speech corpora are descriptive, delimiting intonation units perceived by the listener. We take a novel approach to phrase break prediction for Arabic, deriving our prosodic annotation scheme from Tajwīd (recitation) mark-up in the Qur’an which we then interpret as additional text-based data for computational analysis. This mark-up is prescriptive, and signifies a widely-used recitation style, and one of seven original styles of transmission. Here we report on version 1.0 of our Boundary-Annotated Qur’an dataset of 77430 words and 8230 sentences, where each word is tagged with prosodic and syntactic information at two coarse-grained levels. In (Sawalha et al., 2012), we use the dataset in phrase break prediction experiments. This research is part of a larger-scale project to produce annotation schemes, language resources, algorithms, and applications for Classical and Modern Standard Arabic.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/240_Paper.pdf
%P 1011-1016
Markdown (Informal)
[Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing](http://www.lrec-conf.org/proceedings/lrec2012/pdf/240_Paper.pdf) (Brierley et al., LREC 2012)
ACL