@inproceedings{al-saif-markert-2010-leeds,
title = "The {L}eeds {A}rabic Discourse Treebank: Annotating Discourse Connectives for {A}rabic",
author = "Al-Saif, Amal and
Markert, Katja",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/479_Paper.pdf",
abstract = "We present the first effort towards producing an Arabic Discourse Treebank,a news corpus where all discourse connectives are identified and annotated with the discourse relations they convey as well as with the two arguments they relate. We discuss our collection of Arabic discourse connectives as well as principles for identifying and annotating them in context, taking into account properties specific to Arabic. In particular, we deal with the fact that Arabic has a rich morphology: we therefore include clitics as connectives as well as a wide range of nominalizations as potential arguments. We present a dedicated discourse annotation tool for Arabic and a large-scale annotation study. We show that both the human identification of discourse connectives and the determination of the discourse relations they convey is reliable. Our current annotated corpus encompasses a final 5651 annotated discourse connectives in 537 news texts. In future, we will release the annotated corpus to other researchers and use it for training and testing automated methods for discourse connective and relation recognition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-saif-markert-2010-leeds">
<titleInfo>
<title>The Leeds Arabic Discourse Treebank: Annotating Discourse Connectives for Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Al-Saif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katja</namePart>
<namePart type="family">Markert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the first effort towards producing an Arabic Discourse Treebank,a news corpus where all discourse connectives are identified and annotated with the discourse relations they convey as well as with the two arguments they relate. We discuss our collection of Arabic discourse connectives as well as principles for identifying and annotating them in context, taking into account properties specific to Arabic. In particular, we deal with the fact that Arabic has a rich morphology: we therefore include clitics as connectives as well as a wide range of nominalizations as potential arguments. We present a dedicated discourse annotation tool for Arabic and a large-scale annotation study. We show that both the human identification of discourse connectives and the determination of the discourse relations they convey is reliable. Our current annotated corpus encompasses a final 5651 annotated discourse connectives in 537 news texts. In future, we will release the annotated corpus to other researchers and use it for training and testing automated methods for discourse connective and relation recognition.</abstract>
<identifier type="citekey">al-saif-markert-2010-leeds</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/479_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Leeds Arabic Discourse Treebank: Annotating Discourse Connectives for Arabic
%A Al-Saif, Amal
%A Markert, Katja
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F al-saif-markert-2010-leeds
%X We present the first effort towards producing an Arabic Discourse Treebank,a news corpus where all discourse connectives are identified and annotated with the discourse relations they convey as well as with the two arguments they relate. We discuss our collection of Arabic discourse connectives as well as principles for identifying and annotating them in context, taking into account properties specific to Arabic. In particular, we deal with the fact that Arabic has a rich morphology: we therefore include clitics as connectives as well as a wide range of nominalizations as potential arguments. We present a dedicated discourse annotation tool for Arabic and a large-scale annotation study. We show that both the human identification of discourse connectives and the determination of the discourse relations they convey is reliable. Our current annotated corpus encompasses a final 5651 annotated discourse connectives in 537 news texts. In future, we will release the annotated corpus to other researchers and use it for training and testing automated methods for discourse connective and relation recognition.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/479_Paper.pdf
Markdown (Informal)
[The Leeds Arabic Discourse Treebank: Annotating Discourse Connectives for Arabic](http://www.lrec-conf.org/proceedings/lrec2010/pdf/479_Paper.pdf) (Al-Saif & Markert, LREC 2010)
ACL