@inproceedings{keskes-etal-2012-clause,
title = "Clause-based Discourse Segmentation of {A}rabic Texts",
author = "Keskes, Iskandar and
Benamara, Farah and
Belguith, Lamia Hadrich",
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/939_Paper.pdf",
pages = "2826--2832",
abstract = "This paper describes a rule-based approach to segment Arabic texts into clauses. Our method relies on an extensive analysis of a large set of lexical cues as well as punctuation marks. Our analysis was carried out on two different corpus genres: news articles and elementary school textbooks. We propose a three steps segmentation algorithm: first by using only punctuation marks, then by relying only on lexical cues and finally by using both typology and lexical cues. The results were compared with manual segmentations elaborated by experts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keskes-etal-2012-clause">
<titleInfo>
<title>Clause-based Discourse Segmentation of Arabic Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iskandar</namePart>
<namePart type="family">Keskes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farah</namePart>
<namePart type="family">Benamara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</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>This paper describes a rule-based approach to segment Arabic texts into clauses. Our method relies on an extensive analysis of a large set of lexical cues as well as punctuation marks. Our analysis was carried out on two different corpus genres: news articles and elementary school textbooks. We propose a three steps segmentation algorithm: first by using only punctuation marks, then by relying only on lexical cues and finally by using both typology and lexical cues. The results were compared with manual segmentations elaborated by experts.</abstract>
<identifier type="citekey">keskes-etal-2012-clause</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/939_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2826</start>
<end>2832</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clause-based Discourse Segmentation of Arabic Texts
%A Keskes, Iskandar
%A Benamara, Farah
%A Belguith, Lamia Hadrich
%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 keskes-etal-2012-clause
%X This paper describes a rule-based approach to segment Arabic texts into clauses. Our method relies on an extensive analysis of a large set of lexical cues as well as punctuation marks. Our analysis was carried out on two different corpus genres: news articles and elementary school textbooks. We propose a three steps segmentation algorithm: first by using only punctuation marks, then by relying only on lexical cues and finally by using both typology and lexical cues. The results were compared with manual segmentations elaborated by experts.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/939_Paper.pdf
%P 2826-2832
Markdown (Informal)
[Clause-based Discourse Segmentation of Arabic Texts](http://www.lrec-conf.org/proceedings/lrec2012/pdf/939_Paper.pdf) (Keskes et al., LREC 2012)
ACL
- Iskandar Keskes, Farah Benamara, and Lamia Hadrich Belguith. 2012. Clause-based Discourse Segmentation of Arabic Texts. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2826–2832, Istanbul, Turkey. European Language Resources Association (ELRA).