@inproceedings{civera-juan-ciscar-2008-bilingual,
title = "Bilingual Text Classification using the {IBM} 1 Translation Model",
author = "Civera, Jorge and
Juan-C{\'\i}scar, Alfons",
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/22_paper.pdf",
abstract = "Manual categorisation of documents is a time-consuming task that has been significantly alleviated with the deployment of automatic and machine-aided text categorisation systems. However, the proliferation of multilingual documentation has become a common phenomenon in many international organisations, while most of the current systems have focused on the categorisation of monolingual text. It has been recently shown that the inherent redundancy in bilingual documents can be effectively exploited by relatively simple, bilingual naive Bayes (multinomial) models. In this work, we present a refined version of these models in which this redundancy is explicitly captured by a combination of a unigram (multinomial) model and the well-known IBM 1 translation model. The proposed model is evaluated on two bilingual classification tasks and compared to previous work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="civera-juan-ciscar-2008-bilingual">
<titleInfo>
<title>Bilingual Text Classification using the IBM 1 Translation Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Civera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfons</namePart>
<namePart type="family">Juan-Císcar</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>Manual categorisation of documents is a time-consuming task that has been significantly alleviated with the deployment of automatic and machine-aided text categorisation systems. However, the proliferation of multilingual documentation has become a common phenomenon in many international organisations, while most of the current systems have focused on the categorisation of monolingual text. It has been recently shown that the inherent redundancy in bilingual documents can be effectively exploited by relatively simple, bilingual naive Bayes (multinomial) models. In this work, we present a refined version of these models in which this redundancy is explicitly captured by a combination of a unigram (multinomial) model and the well-known IBM 1 translation model. The proposed model is evaluated on two bilingual classification tasks and compared to previous work.</abstract>
<identifier type="citekey">civera-juan-ciscar-2008-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/22_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Text Classification using the IBM 1 Translation Model
%A Civera, Jorge
%A Juan-Císcar, Alfons
%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 civera-juan-ciscar-2008-bilingual
%X Manual categorisation of documents is a time-consuming task that has been significantly alleviated with the deployment of automatic and machine-aided text categorisation systems. However, the proliferation of multilingual documentation has become a common phenomenon in many international organisations, while most of the current systems have focused on the categorisation of monolingual text. It has been recently shown that the inherent redundancy in bilingual documents can be effectively exploited by relatively simple, bilingual naive Bayes (multinomial) models. In this work, we present a refined version of these models in which this redundancy is explicitly captured by a combination of a unigram (multinomial) model and the well-known IBM 1 translation model. The proposed model is evaluated on two bilingual classification tasks and compared to previous work.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/22_paper.pdf
Markdown (Informal)
[Bilingual Text Classification using the IBM 1 Translation Model](http://www.lrec-conf.org/proceedings/lrec2008/pdf/22_paper.pdf) (Civera & Juan-Císcar, LREC 2008)
ACL