@inproceedings{hasan-ney-2008-multi,
title = "A Multi-Genre {SMT} System for {A}rabic to {F}rench",
author = "Hasan, Sa{\v{s}}a and
Ney, Hermann",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/549_paper.pdf",
abstract = "This work presents improvements of a large-scale Arabic to French statistical machine translation system over a period of three years. The development includes better preprocessing, more training data, additional genre-specific tuning for different domains, namely newswire text and broadcast news transcripts, and improved domain-dependent language models. Starting with an early prototype in 2005 that participated in the second CESTA evaluation, the system was further upgraded to achieve favorable BLEU scores of 44.8{\%} for the text and 41.1{\%} for the audio setting. These results are compared to a system based on the freely available Moses toolkit. We show significant gains both in terms of translation quality (up to +1.2{\%} BLEU absolute) and translation speed (up to 16 times faster) for comparable configuration settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-ney-2008-multi">
<titleInfo>
<title>A Multi-Genre SMT System for Arabic to French</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">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work presents improvements of a large-scale Arabic to French statistical machine translation system over a period of three years. The development includes better preprocessing, more training data, additional genre-specific tuning for different domains, namely newswire text and broadcast news transcripts, and improved domain-dependent language models. Starting with an early prototype in 2005 that participated in the second CESTA evaluation, the system was further upgraded to achieve favorable BLEU scores of 44.8% for the text and 41.1% for the audio setting. These results are compared to a system based on the freely available Moses toolkit. We show significant gains both in terms of translation quality (up to +1.2% BLEU absolute) and translation speed (up to 16 times faster) for comparable configuration settings.</abstract>
<identifier type="citekey">hasan-ney-2008-multi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/549_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Genre SMT System for Arabic to French
%A Hasan, Saša
%A Ney, Hermann
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F hasan-ney-2008-multi
%X This work presents improvements of a large-scale Arabic to French statistical machine translation system over a period of three years. The development includes better preprocessing, more training data, additional genre-specific tuning for different domains, namely newswire text and broadcast news transcripts, and improved domain-dependent language models. Starting with an early prototype in 2005 that participated in the second CESTA evaluation, the system was further upgraded to achieve favorable BLEU scores of 44.8% for the text and 41.1% for the audio setting. These results are compared to a system based on the freely available Moses toolkit. We show significant gains both in terms of translation quality (up to +1.2% BLEU absolute) and translation speed (up to 16 times faster) for comparable configuration settings.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/549_paper.pdf
Markdown (Informal)
[A Multi-Genre SMT System for Arabic to French](http://www.lrec-conf.org/proceedings/lrec2008/pdf/549_paper.pdf) (Hasan & Ney, LREC 2008)
ACL
- Saša Hasan and Hermann Ney. 2008. A Multi-Genre SMT System for Arabic to French. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).