@inproceedings{maamouri-etal-2010-speech,
title = "From Speech to Trees: Applying Treebank Annotation to {A}rabic Broadcast News",
author = "Maamouri, Mohamed and
Bies, Ann and
Kulick, Seth and
Zaghouani, Wajdi and
Graff, Dave and
Ciul, Mike",
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/558_Paper.pdf",
abstract = "The Arabic Treebank (ATB) Project at the Linguistic Data Consortium (LDC) has embarked on a large corpus of Broadcast News (BN) transcriptions, and this has led to a number of new challenges for the data processing and annotation procedures that were originally developed for Arabic newswire text (ATB1, ATB2 and ATB3). The corpus requirements currently posed by the DARPA GALE Program, including English translation of Arabic BN transcripts, word-level alignment of Arabic and English data, and creation of a corresponding English Treebank, place significant new constraints on ATB corpus creation, and require careful coordination among a wide assortment of concurrent activities and participants. Nonetheless, in spite of the new challenges posed by BN data, the ATBs newly improved pipeline and revised annotation guidelines for newswire have proven to be robust enough that very few changes were necessary to account for the new genre of data. This paper presents the points where some adaptation has been necessary, and the overall pipeline as used in the production of BN ATB data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maamouri-etal-2010-speech">
<titleInfo>
<title>From Speech to Trees: Applying Treebank Annotation to Arabic Broadcast News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Maamouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Bies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Kulick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dave</namePart>
<namePart type="family">Graff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Ciul</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>The Arabic Treebank (ATB) Project at the Linguistic Data Consortium (LDC) has embarked on a large corpus of Broadcast News (BN) transcriptions, and this has led to a number of new challenges for the data processing and annotation procedures that were originally developed for Arabic newswire text (ATB1, ATB2 and ATB3). The corpus requirements currently posed by the DARPA GALE Program, including English translation of Arabic BN transcripts, word-level alignment of Arabic and English data, and creation of a corresponding English Treebank, place significant new constraints on ATB corpus creation, and require careful coordination among a wide assortment of concurrent activities and participants. Nonetheless, in spite of the new challenges posed by BN data, the ATBs newly improved pipeline and revised annotation guidelines for newswire have proven to be robust enough that very few changes were necessary to account for the new genre of data. This paper presents the points where some adaptation has been necessary, and the overall pipeline as used in the production of BN ATB data.</abstract>
<identifier type="citekey">maamouri-etal-2010-speech</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/558_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Speech to Trees: Applying Treebank Annotation to Arabic Broadcast News
%A Maamouri, Mohamed
%A Bies, Ann
%A Kulick, Seth
%A Zaghouani, Wajdi
%A Graff, Dave
%A Ciul, Mike
%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 maamouri-etal-2010-speech
%X The Arabic Treebank (ATB) Project at the Linguistic Data Consortium (LDC) has embarked on a large corpus of Broadcast News (BN) transcriptions, and this has led to a number of new challenges for the data processing and annotation procedures that were originally developed for Arabic newswire text (ATB1, ATB2 and ATB3). The corpus requirements currently posed by the DARPA GALE Program, including English translation of Arabic BN transcripts, word-level alignment of Arabic and English data, and creation of a corresponding English Treebank, place significant new constraints on ATB corpus creation, and require careful coordination among a wide assortment of concurrent activities and participants. Nonetheless, in spite of the new challenges posed by BN data, the ATBs newly improved pipeline and revised annotation guidelines for newswire have proven to be robust enough that very few changes were necessary to account for the new genre of data. This paper presents the points where some adaptation has been necessary, and the overall pipeline as used in the production of BN ATB data.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/558_Paper.pdf
Markdown (Informal)
[From Speech to Trees: Applying Treebank Annotation to Arabic Broadcast News](http://www.lrec-conf.org/proceedings/lrec2010/pdf/558_Paper.pdf) (Maamouri et al., LREC 2010)
ACL