@inproceedings{maamouri-etal-2012-expanding,
title = "Expanding {A}rabic Treebank to Speech: Results from Broadcast News",
author = "Maamouri, Mohamed and
Bies, Ann and
Kulick, Seth",
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/557_Paper.pdf",
pages = "1856--1861",
abstract = "Treebanking a large corpus of relatively structured speech transcribed from various Arabic Broadcast News (BN) sources has allowed us to begin to address the many challenges of annotating and parsing a speech corpus in Arabic. The now completed Arabic Treebank BN corpus consists of 432,976 source tokens (517,080 tree tokens) in 120 files of manually transcribed news broadcasts. Because news broadcasts are predominantly scripted, most of the transcribed speech is in Modern Standard Arabic (MSA). As such, the lexical and syntactic structures are very similar to the MSA in written newswire data. However, because this is spoken news, cross-linguistic speech effects such as restarts, fillers, hesitations, and repetitions are common. There is also a certain amount of dialect data present in the BN corpus, from on-the-street interviews and similar informal contexts. In this paper, we describe the finished corpus and focus on some of the necessary additions to our annotation guidelines, along with some of the technical challenges of a treebanked speech corpus and an initial parsing evaluation for this data. This corpus will be available to the community in 2012 as an LDC publication.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maamouri-etal-2012-expanding">
<titleInfo>
<title>Expanding Arabic Treebank to Speech: Results from 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>
<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>Treebanking a large corpus of relatively structured speech transcribed from various Arabic Broadcast News (BN) sources has allowed us to begin to address the many challenges of annotating and parsing a speech corpus in Arabic. The now completed Arabic Treebank BN corpus consists of 432,976 source tokens (517,080 tree tokens) in 120 files of manually transcribed news broadcasts. Because news broadcasts are predominantly scripted, most of the transcribed speech is in Modern Standard Arabic (MSA). As such, the lexical and syntactic structures are very similar to the MSA in written newswire data. However, because this is spoken news, cross-linguistic speech effects such as restarts, fillers, hesitations, and repetitions are common. There is also a certain amount of dialect data present in the BN corpus, from on-the-street interviews and similar informal contexts. In this paper, we describe the finished corpus and focus on some of the necessary additions to our annotation guidelines, along with some of the technical challenges of a treebanked speech corpus and an initial parsing evaluation for this data. This corpus will be available to the community in 2012 as an LDC publication.</abstract>
<identifier type="citekey">maamouri-etal-2012-expanding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/557_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1856</start>
<end>1861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Expanding Arabic Treebank to Speech: Results from Broadcast News
%A Maamouri, Mohamed
%A Bies, Ann
%A Kulick, Seth
%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 maamouri-etal-2012-expanding
%X Treebanking a large corpus of relatively structured speech transcribed from various Arabic Broadcast News (BN) sources has allowed us to begin to address the many challenges of annotating and parsing a speech corpus in Arabic. The now completed Arabic Treebank BN corpus consists of 432,976 source tokens (517,080 tree tokens) in 120 files of manually transcribed news broadcasts. Because news broadcasts are predominantly scripted, most of the transcribed speech is in Modern Standard Arabic (MSA). As such, the lexical and syntactic structures are very similar to the MSA in written newswire data. However, because this is spoken news, cross-linguistic speech effects such as restarts, fillers, hesitations, and repetitions are common. There is also a certain amount of dialect data present in the BN corpus, from on-the-street interviews and similar informal contexts. In this paper, we describe the finished corpus and focus on some of the necessary additions to our annotation guidelines, along with some of the technical challenges of a treebanked speech corpus and an initial parsing evaluation for this data. This corpus will be available to the community in 2012 as an LDC publication.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/557_Paper.pdf
%P 1856-1861
Markdown (Informal)
[Expanding Arabic Treebank to Speech: Results from Broadcast News](http://www.lrec-conf.org/proceedings/lrec2012/pdf/557_Paper.pdf) (Maamouri et al., LREC 2012)
ACL