@inproceedings{maamouri-etal-2006-developing,
title = "Developing and Using a Pilot Dialectal {A}rabic Treebank",
author = "Maamouri, Mohamed and
Bies, Ann and
Buckwalter, Tim and
Diab, Mona and
Habash, Nizar and
Rambow, Owen and
Tabessi, Dalila",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.pdf",
abstract = "In this paper, we describe the methodological procedures and issues that emerged from the development of a pilot Levantine Arabic Treebank (LATB) at the Linguistic Data Consortium (LDC) and its use at the Johns Hopkins University (JHU) Center for Language and Speech Processing workshop on Parsing Arabic Dialects (PAD). This pilot, consisting of morphological and syntactic annotation of approximately 26,000 words of Levantine Arabic conversational telephone speech, was developed under severe time constraints; hence the LDC team drew on their experience in treebanking Modern Standard Arabic (MSA) text. The resulting Levantine dialect treebanked corpus was used by the PAD team to develop and evaluate parsers for Levantine dialect texts. The parsers were trained on MSA resources and adapted using dialect-MSA lexical resources (some developed especially for this task) and existing linguistic knowledge about syntactic differences between MSA and dialect. The use of the LATB for development and evaluation of syntactic parsers allowed the PAD team to provide feedbasck to the LDC treebank developers. In this paper, we describe the creation of resources for this corpus, as well as transformations on the corpus to eliminate speech effects and lessen the gap between our pre-existing MSA resources and the new dialectal corpus",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maamouri-etal-2006-developing">
<titleInfo>
<title>Developing and Using a Pilot Dialectal Arabic Treebank</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">Tim</namePart>
<namePart type="family">Buckwalter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dalila</namePart>
<namePart type="family">Tabessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe the methodological procedures and issues that emerged from the development of a pilot Levantine Arabic Treebank (LATB) at the Linguistic Data Consortium (LDC) and its use at the Johns Hopkins University (JHU) Center for Language and Speech Processing workshop on Parsing Arabic Dialects (PAD). This pilot, consisting of morphological and syntactic annotation of approximately 26,000 words of Levantine Arabic conversational telephone speech, was developed under severe time constraints; hence the LDC team drew on their experience in treebanking Modern Standard Arabic (MSA) text. The resulting Levantine dialect treebanked corpus was used by the PAD team to develop and evaluate parsers for Levantine dialect texts. The parsers were trained on MSA resources and adapted using dialect-MSA lexical resources (some developed especially for this task) and existing linguistic knowledge about syntactic differences between MSA and dialect. The use of the LATB for development and evaluation of syntactic parsers allowed the PAD team to provide feedbasck to the LDC treebank developers. In this paper, we describe the creation of resources for this corpus, as well as transformations on the corpus to eliminate speech effects and lessen the gap between our pre-existing MSA resources and the new dialectal corpus</abstract>
<identifier type="citekey">maamouri-etal-2006-developing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing and Using a Pilot Dialectal Arabic Treebank
%A Maamouri, Mohamed
%A Bies, Ann
%A Buckwalter, Tim
%A Diab, Mona
%A Habash, Nizar
%A Rambow, Owen
%A Tabessi, Dalila
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F maamouri-etal-2006-developing
%X In this paper, we describe the methodological procedures and issues that emerged from the development of a pilot Levantine Arabic Treebank (LATB) at the Linguistic Data Consortium (LDC) and its use at the Johns Hopkins University (JHU) Center for Language and Speech Processing workshop on Parsing Arabic Dialects (PAD). This pilot, consisting of morphological and syntactic annotation of approximately 26,000 words of Levantine Arabic conversational telephone speech, was developed under severe time constraints; hence the LDC team drew on their experience in treebanking Modern Standard Arabic (MSA) text. The resulting Levantine dialect treebanked corpus was used by the PAD team to develop and evaluate parsers for Levantine dialect texts. The parsers were trained on MSA resources and adapted using dialect-MSA lexical resources (some developed especially for this task) and existing linguistic knowledge about syntactic differences between MSA and dialect. The use of the LATB for development and evaluation of syntactic parsers allowed the PAD team to provide feedbasck to the LDC treebank developers. In this paper, we describe the creation of resources for this corpus, as well as transformations on the corpus to eliminate speech effects and lessen the gap between our pre-existing MSA resources and the new dialectal corpus
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.pdf
Markdown (Informal)
[Developing and Using a Pilot Dialectal Arabic Treebank](http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.pdf) (Maamouri et al., LREC 2006)
ACL
- Mohamed Maamouri, Ann Bies, Tim Buckwalter, Mona Diab, Nizar Habash, Owen Rambow, and Dalila Tabessi. 2006. Developing and Using a Pilot Dialectal Arabic Treebank. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).