@inproceedings{boxwell-brew-2010-pilot,
title = "A Pilot {A}rabic {CCG}bank",
author = "Boxwell, Stephen A. and
Brew, Chris",
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 = "https://aclanthology.org/L10-1429/",
abstract = "We describe a process for converting the Penn Arabic Treebank into the CCG formalism. Previous efforts have yielded CCGbanks in English, German, and Turkish, thus opening these languages to the sophisticated computational tools developed for CCG and enabling further cross-linguistic development. Conversion from a context free grammar treebank to a CCGbank is a four stage process: head finding, argument classification, binarization, and category conversion. In the process of implementing a basic CCGbank conversion algorithm, we reveal properties of Arabic grammar that interfere with conversion, such as subject topicalization, genitive constructions, relative clauses, and optional pronominal subjects. All of these problematic phenomena can be resolved in a variety of ways - we discuss advantages and disadvantages of each in their respective sections. We detail these and describe our categorial analysis of each of these Arabic grammatical phenomena in depth, as well as technical details on their integration into the conversion algorithm."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boxwell-brew-2010-pilot">
<titleInfo>
<title>A Pilot Arabic CCGbank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Boxwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brew</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 describe a process for converting the Penn Arabic Treebank into the CCG formalism. Previous efforts have yielded CCGbanks in English, German, and Turkish, thus opening these languages to the sophisticated computational tools developed for CCG and enabling further cross-linguistic development. Conversion from a context free grammar treebank to a CCGbank is a four stage process: head finding, argument classification, binarization, and category conversion. In the process of implementing a basic CCGbank conversion algorithm, we reveal properties of Arabic grammar that interfere with conversion, such as subject topicalization, genitive constructions, relative clauses, and optional pronominal subjects. All of these problematic phenomena can be resolved in a variety of ways - we discuss advantages and disadvantages of each in their respective sections. We detail these and describe our categorial analysis of each of these Arabic grammatical phenomena in depth, as well as technical details on their integration into the conversion algorithm.</abstract>
<identifier type="citekey">boxwell-brew-2010-pilot</identifier>
<location>
<url>https://aclanthology.org/L10-1429/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pilot Arabic CCGbank
%A Boxwell, Stephen A.
%A Brew, Chris
%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 boxwell-brew-2010-pilot
%X We describe a process for converting the Penn Arabic Treebank into the CCG formalism. Previous efforts have yielded CCGbanks in English, German, and Turkish, thus opening these languages to the sophisticated computational tools developed for CCG and enabling further cross-linguistic development. Conversion from a context free grammar treebank to a CCGbank is a four stage process: head finding, argument classification, binarization, and category conversion. In the process of implementing a basic CCGbank conversion algorithm, we reveal properties of Arabic grammar that interfere with conversion, such as subject topicalization, genitive constructions, relative clauses, and optional pronominal subjects. All of these problematic phenomena can be resolved in a variety of ways - we discuss advantages and disadvantages of each in their respective sections. We detail these and describe our categorial analysis of each of these Arabic grammatical phenomena in depth, as well as technical details on their integration into the conversion algorithm.
%U https://aclanthology.org/L10-1429/
Markdown (Informal)
[A Pilot Arabic CCGbank](https://aclanthology.org/L10-1429/) (Boxwell & Brew, LREC 2010)
ACL
- Stephen A. Boxwell and Chris Brew. 2010. A Pilot Arabic CCGbank. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).