@inproceedings{gahbiche-braham-etal-2012-joint,
title = "Joint Segmentation and {POS} Tagging for {A}rabic Using a {CRF}-based Classifier",
author = "Gahbiche-Braham, Souhir and
Bonneau-Maynard, H{\'e}l{\`e}ne and
Lavergne, Thomas and
Yvon, Fran{\c{c}}ois",
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 = "https://aclanthology.org/L12-1509/",
pages = "2107--2113",
abstract = "Arabic is a morphologically rich language, and Arabic texts abound of complex word forms built by concatenation of multiple subparts, corresponding for instance to prepositions, articles, roots prefixes, or suffixes. The development of Arabic Natural Language Processing applications, such as Machine Translation (MT) tools, thus requires some kind of morphological analysis. In this paper, we compare various strategies for performing such preprocessing, using generic machine learning techniques. The resulting tool is compared with two open domain alternatives in the context of a statistical MT task and is shown to be faster than its competitors, with no significant difference in MT quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gahbiche-braham-etal-2012-joint">
<titleInfo>
<title>Joint Segmentation and POS Tagging for Arabic Using a CRF-based Classifier</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souhir</namePart>
<namePart type="family">Gahbiche-Braham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Bonneau-Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Lavergne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</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>Arabic is a morphologically rich language, and Arabic texts abound of complex word forms built by concatenation of multiple subparts, corresponding for instance to prepositions, articles, roots prefixes, or suffixes. The development of Arabic Natural Language Processing applications, such as Machine Translation (MT) tools, thus requires some kind of morphological analysis. In this paper, we compare various strategies for performing such preprocessing, using generic machine learning techniques. The resulting tool is compared with two open domain alternatives in the context of a statistical MT task and is shown to be faster than its competitors, with no significant difference in MT quality.</abstract>
<identifier type="citekey">gahbiche-braham-etal-2012-joint</identifier>
<location>
<url>https://aclanthology.org/L12-1509/</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2107</start>
<end>2113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Segmentation and POS Tagging for Arabic Using a CRF-based Classifier
%A Gahbiche-Braham, Souhir
%A Bonneau-Maynard, Hélène
%A Lavergne, Thomas
%A Yvon, François
%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 gahbiche-braham-etal-2012-joint
%X Arabic is a morphologically rich language, and Arabic texts abound of complex word forms built by concatenation of multiple subparts, corresponding for instance to prepositions, articles, roots prefixes, or suffixes. The development of Arabic Natural Language Processing applications, such as Machine Translation (MT) tools, thus requires some kind of morphological analysis. In this paper, we compare various strategies for performing such preprocessing, using generic machine learning techniques. The resulting tool is compared with two open domain alternatives in the context of a statistical MT task and is shown to be faster than its competitors, with no significant difference in MT quality.
%U https://aclanthology.org/L12-1509/
%P 2107-2113
Markdown (Informal)
[Joint Segmentation and POS Tagging for Arabic Using a CRF-based Classifier](https://aclanthology.org/L12-1509/) (Gahbiche-Braham et al., LREC 2012)
ACL