@inproceedings{rosner-sultana-2014-automatic,
title = "Automatic Methods for the Extension of a Bilingual Dictionary using Comparable Corpora",
author = "Rosner, Michael and
Sultana, Kurt",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1169_Paper.pdf",
pages = "3790--3797",
abstract = "Bilingual dictionaries define word equivalents from one language to another, thus acting as an important bridge between languages. No bilingual dictionary is complete since languages are in a constant state of change. Additionally, dictionaries are unlikely to achieve complete coverage of all language terms. This paper investigates methods for extending dictionaries using non-aligned corpora, by finding translations through context similarity. Most methods compute word contexts from general corpora. This can lead to errors due to data sparsity. We investigate the hypothesis that this problem can be addressed by carefully choosing smaller corpora in which domain-specific terms are more predominant. We also introduce the notion of efficiency which we consider as the effort required to obtain a set of dictionary entries from a given corpus",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosner-sultana-2014-automatic">
<titleInfo>
<title>Automatic Methods for the Extension of a Bilingual Dictionary using Comparable Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Sultana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bilingual dictionaries define word equivalents from one language to another, thus acting as an important bridge between languages. No bilingual dictionary is complete since languages are in a constant state of change. Additionally, dictionaries are unlikely to achieve complete coverage of all language terms. This paper investigates methods for extending dictionaries using non-aligned corpora, by finding translations through context similarity. Most methods compute word contexts from general corpora. This can lead to errors due to data sparsity. We investigate the hypothesis that this problem can be addressed by carefully choosing smaller corpora in which domain-specific terms are more predominant. We also introduce the notion of efficiency which we consider as the effort required to obtain a set of dictionary entries from a given corpus</abstract>
<identifier type="citekey">rosner-sultana-2014-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1169_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3790</start>
<end>3797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Methods for the Extension of a Bilingual Dictionary using Comparable Corpora
%A Rosner, Michael
%A Sultana, Kurt
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F rosner-sultana-2014-automatic
%X Bilingual dictionaries define word equivalents from one language to another, thus acting as an important bridge between languages. No bilingual dictionary is complete since languages are in a constant state of change. Additionally, dictionaries are unlikely to achieve complete coverage of all language terms. This paper investigates methods for extending dictionaries using non-aligned corpora, by finding translations through context similarity. Most methods compute word contexts from general corpora. This can lead to errors due to data sparsity. We investigate the hypothesis that this problem can be addressed by carefully choosing smaller corpora in which domain-specific terms are more predominant. We also introduce the notion of efficiency which we consider as the effort required to obtain a set of dictionary entries from a given corpus
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1169_Paper.pdf
%P 3790-3797
Markdown (Informal)
[Automatic Methods for the Extension of a Bilingual Dictionary using Comparable Corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1169_Paper.pdf) (Rosner & Sultana, LREC 2014)
ACL