@inproceedings{sawalha-etal-2012-predicting,
title = "Predicting Phrase Breaks in Classical and {M}odern {S}tandard {A}rabic Text",
author = "Sawalha, Majdi and
Brierley, Claire 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/239_Paper.pdf",
pages = "3868--3872",
abstract = "We train and test two probabilistic taggers for Arabic phrase break prediction on a purpose-built, gold standard, boundary-annotated and PoS-tagged Qur'an corpus of 77430 words and 8230 sentences. In a related LREC paper (Brierley et al., 2012), we cover dataset build. Here we report on comparative experiments with off-the-shelf N-gram and HMM taggers and coarse-grained feature sets for syntax and prosody, where the task is to predict boundary locations in an unseen test set stripped of boundary annotations by classifying words as breaks or non-breaks. The preponderance of non-breaks in the training data sets a challenging baseline success rate: 85.56{\%}. However, we achieve significant gains in accuracy with the trigram tagger, and significant gains in performance recognition of minority class instances with both taggers via Balanced Classification Rate. This is initial work on a long-term research 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="sawalha-etal-2012-predicting">
<titleInfo>
<title>Predicting Phrase Breaks in Classical and Modern Standard Arabic Text</title>
</titleInfo>
<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">Claire</namePart>
<namePart type="family">Brierley</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>We train and test two probabilistic taggers for Arabic phrase break prediction on a purpose-built, gold standard, boundary-annotated and PoS-tagged Qur’an corpus of 77430 words and 8230 sentences. In a related LREC paper (Brierley et al., 2012), we cover dataset build. Here we report on comparative experiments with off-the-shelf N-gram and HMM taggers and coarse-grained feature sets for syntax and prosody, where the task is to predict boundary locations in an unseen test set stripped of boundary annotations by classifying words as breaks or non-breaks. The preponderance of non-breaks in the training data sets a challenging baseline success rate: 85.56%. However, we achieve significant gains in accuracy with the trigram tagger, and significant gains in performance recognition of minority class instances with both taggers via Balanced Classification Rate. This is initial work on a long-term research project to produce annotation schemes, language resources, algorithms, and applications for Classical and Modern Standard Arabic.</abstract>
<identifier type="citekey">sawalha-etal-2012-predicting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3868</start>
<end>3872</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Phrase Breaks in Classical and Modern Standard Arabic Text
%A Sawalha, Majdi
%A Brierley, Claire
%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 sawalha-etal-2012-predicting
%X We train and test two probabilistic taggers for Arabic phrase break prediction on a purpose-built, gold standard, boundary-annotated and PoS-tagged Qur’an corpus of 77430 words and 8230 sentences. In a related LREC paper (Brierley et al., 2012), we cover dataset build. Here we report on comparative experiments with off-the-shelf N-gram and HMM taggers and coarse-grained feature sets for syntax and prosody, where the task is to predict boundary locations in an unseen test set stripped of boundary annotations by classifying words as breaks or non-breaks. The preponderance of non-breaks in the training data sets a challenging baseline success rate: 85.56%. However, we achieve significant gains in accuracy with the trigram tagger, and significant gains in performance recognition of minority class instances with both taggers via Balanced Classification Rate. This is initial work on a long-term research 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/239_Paper.pdf
%P 3868-3872
Markdown (Informal)
[Predicting Phrase Breaks in Classical and Modern Standard Arabic Text](http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf) (Sawalha et al., LREC 2012)
ACL