@inproceedings{hasan-etal-2006-creating,
title = "Creating a Large-Scale {A}rabic to {F}rench Statistical {M}achine{T}ranslation System",
author = "Hasan, Sa{\v{s}}a and
Isbihani, Anas El and
Ney, Hermann",
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/405_pdf.pdf",
abstract = "In this work, the creation of a large-scale Arabic to French statistical machine translation system is presented. We introduce all necessary steps from corpus aquisition, preprocessing the data to training and optimizing the system and eventual evaluation. Since no corpora existed previously, we collected large amounts of data from the web. Arabic word segmentation was crucial to reduce the overall number of unknown words. We describe the phrase-based SMT system used for training and generation of the translation hypotheses. Results on the second CESTA evaluation campaign are reported. The setting was inthe medical domain. The prototype reaches a favorable BLEU score of40.8{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-etal-2006-creating">
<titleInfo>
<title>Creating a Large-Scale Arabic to French Statistical MachineTranslation System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saša</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="given">El</namePart>
<namePart type="family">Isbihani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</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 work, the creation of a large-scale Arabic to French statistical machine translation system is presented. We introduce all necessary steps from corpus aquisition, preprocessing the data to training and optimizing the system and eventual evaluation. Since no corpora existed previously, we collected large amounts of data from the web. Arabic word segmentation was crucial to reduce the overall number of unknown words. We describe the phrase-based SMT system used for training and generation of the translation hypotheses. Results on the second CESTA evaluation campaign are reported. The setting was inthe medical domain. The prototype reaches a favorable BLEU score of40.8%.</abstract>
<identifier type="citekey">hasan-etal-2006-creating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/405_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Large-Scale Arabic to French Statistical MachineTranslation System
%A Hasan, Saša
%A Isbihani, Anas El
%A Ney, Hermann
%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 hasan-etal-2006-creating
%X In this work, the creation of a large-scale Arabic to French statistical machine translation system is presented. We introduce all necessary steps from corpus aquisition, preprocessing the data to training and optimizing the system and eventual evaluation. Since no corpora existed previously, we collected large amounts of data from the web. Arabic word segmentation was crucial to reduce the overall number of unknown words. We describe the phrase-based SMT system used for training and generation of the translation hypotheses. Results on the second CESTA evaluation campaign are reported. The setting was inthe medical domain. The prototype reaches a favorable BLEU score of40.8%.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/405_pdf.pdf
Markdown (Informal)
[Creating a Large-Scale Arabic to French Statistical MachineTranslation System](http://www.lrec-conf.org/proceedings/lrec2006/pdf/405_pdf.pdf) (Hasan et al., LREC 2006)
ACL