@inproceedings{benajiba-zitouni-2010-arabic,
title = "{A}rabic Word Segmentation for Better Unit of Analysis",
author = "Benajiba, Yassine and
Zitouni, Imed",
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/54_Paper.pdf",
abstract = "The Arabic language has a very rich morphology where a word is composed of zero or more prefixes, a stem and zero or more suffixes. This makes Arabic data sparse compared to other languages, such as English, and consequently word segmentation becomes very important for many Natural Language Processing tasks that deal with the Arabic language. We present in this paper two segmentation schemes that are morphological segmentation and Arabic TreeBank segmentation and we show their impact on an important natural language processing task that is mention detection. Experiments on Arabic TreeBank corpus show 98.1{\%} accuracy on morphological segmentation and 99.4{\%} on morphological segmentation. We also discuss the importance of segmenting the text; experiments show up to 6F points improvement of the mention detection system performance when morphological segmentation is used instead of not segmenting the text. Obtained results also show up to 3F points improvement is achieved when the appropriate segmentation style is used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benajiba-zitouni-2010-arabic">
<titleInfo>
<title>Arabic Word Segmentation for Better Unit of Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yassine</namePart>
<namePart type="family">Benajiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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 language has a very rich morphology where a word is composed of zero or more prefixes, a stem and zero or more suffixes. This makes Arabic data sparse compared to other languages, such as English, and consequently word segmentation becomes very important for many Natural Language Processing tasks that deal with the Arabic language. We present in this paper two segmentation schemes that are morphological segmentation and Arabic TreeBank segmentation and we show their impact on an important natural language processing task that is mention detection. Experiments on Arabic TreeBank corpus show 98.1% accuracy on morphological segmentation and 99.4% on morphological segmentation. We also discuss the importance of segmenting the text; experiments show up to 6F points improvement of the mention detection system performance when morphological segmentation is used instead of not segmenting the text. Obtained results also show up to 3F points improvement is achieved when the appropriate segmentation style is used.</abstract>
<identifier type="citekey">benajiba-zitouni-2010-arabic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/54_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Word Segmentation for Better Unit of Analysis
%A Benajiba, Yassine
%A Zitouni, Imed
%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 benajiba-zitouni-2010-arabic
%X The Arabic language has a very rich morphology where a word is composed of zero or more prefixes, a stem and zero or more suffixes. This makes Arabic data sparse compared to other languages, such as English, and consequently word segmentation becomes very important for many Natural Language Processing tasks that deal with the Arabic language. We present in this paper two segmentation schemes that are morphological segmentation and Arabic TreeBank segmentation and we show their impact on an important natural language processing task that is mention detection. Experiments on Arabic TreeBank corpus show 98.1% accuracy on morphological segmentation and 99.4% on morphological segmentation. We also discuss the importance of segmenting the text; experiments show up to 6F points improvement of the mention detection system performance when morphological segmentation is used instead of not segmenting the text. Obtained results also show up to 3F points improvement is achieved when the appropriate segmentation style is used.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/54_Paper.pdf
Markdown (Informal)
[Arabic Word Segmentation for Better Unit of Analysis](http://www.lrec-conf.org/proceedings/lrec2010/pdf/54_Paper.pdf) (Benajiba & Zitouni, LREC 2010)
ACL
- Yassine Benajiba and Imed Zitouni. 2010. Arabic Word Segmentation for Better Unit of Analysis. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).