@inproceedings{civera-juan-2006-bilingual,
title = "Bilingual Machine-Aided Indexing",
author = "Civera, Jorge and
Juan, Alfons",
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/304_pdf.pdf",
abstract = "The proliferation of multilingual documentation in our Information Society has become a common phenomenon. This documentation is usually categorised by hand, entailing a time-consuming and arduous burden. This is particularly true in the case of keyword assignment, in which a list of keywords (descriptors) from a controlled vocabulary (thesaurus) is assigned to a document. A possible solution to alleviate this problem comes from the hand of the so-called Machine-Aided Indexing (MAI) systems. These systems work in cooperation with professional indexer by providing a initial list of descriptors from which those most appropiated will be selected. This way of proceeding increases the productivity and eases the task of indexers. In this paper, we propose a statistical text classification framework for bilingual documentation, from which we derive two novel bilingual classifiers based on the naive combination of monolingual classifiers. We report preliminary results on the multilingual corpus Acquis Communautaire (AC) that demonstrates the suitability of the proposed classifiers as the backend of a fully-working MAI system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="civera-juan-2006-bilingual">
<titleInfo>
<title>Bilingual Machine-Aided Indexing</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</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>The proliferation of multilingual documentation in our Information Society has become a common phenomenon. This documentation is usually categorised by hand, entailing a time-consuming and arduous burden. This is particularly true in the case of keyword assignment, in which a list of keywords (descriptors) from a controlled vocabulary (thesaurus) is assigned to a document. A possible solution to alleviate this problem comes from the hand of the so-called Machine-Aided Indexing (MAI) systems. These systems work in cooperation with professional indexer by providing a initial list of descriptors from which those most appropiated will be selected. This way of proceeding increases the productivity and eases the task of indexers. In this paper, we propose a statistical text classification framework for bilingual documentation, from which we derive two novel bilingual classifiers based on the naive combination of monolingual classifiers. We report preliminary results on the multilingual corpus Acquis Communautaire (AC) that demonstrates the suitability of the proposed classifiers as the backend of a fully-working MAI system.</abstract>
<identifier type="citekey">civera-juan-2006-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/304_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Machine-Aided Indexing
%A Civera, Jorge
%A Juan, Alfons
%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 civera-juan-2006-bilingual
%X The proliferation of multilingual documentation in our Information Society has become a common phenomenon. This documentation is usually categorised by hand, entailing a time-consuming and arduous burden. This is particularly true in the case of keyword assignment, in which a list of keywords (descriptors) from a controlled vocabulary (thesaurus) is assigned to a document. A possible solution to alleviate this problem comes from the hand of the so-called Machine-Aided Indexing (MAI) systems. These systems work in cooperation with professional indexer by providing a initial list of descriptors from which those most appropiated will be selected. This way of proceeding increases the productivity and eases the task of indexers. In this paper, we propose a statistical text classification framework for bilingual documentation, from which we derive two novel bilingual classifiers based on the naive combination of monolingual classifiers. We report preliminary results on the multilingual corpus Acquis Communautaire (AC) that demonstrates the suitability of the proposed classifiers as the backend of a fully-working MAI system.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/304_pdf.pdf
Markdown (Informal)
[Bilingual Machine-Aided Indexing](http://www.lrec-conf.org/proceedings/lrec2006/pdf/304_pdf.pdf) (Civera & Juan, LREC 2006)
ACL
- Jorge Civera and Alfons Juan. 2006. Bilingual Machine-Aided Indexing. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).