@inproceedings{rapp-etal-2012-identifying,
title = "Identifying Word Translations from Comparable Documents Without a Seed Lexicon",
author = "Rapp, Reinhard and
Sharoff, Serge and
Babych, Bogdan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/888_Paper.pdf",
pages = "460--466",
abstract = "The extraction of dictionaries from parallel text corpora is an established technique. However, as parallel corpora are a scarce resource, in recent years the extraction of dictionaries using comparable corpora has obtained increasing attention. In order to find a mapping between languages, almost all approaches suggested in the literature rely on a seed lexicon. The work described here achieves competitive results without requiring such a seed lexicon. Instead it presupposes mappings between comparable documents in different languages. For some common types of textual resources (e.g. encyclopedias or newspaper texts) such mappings are either readily available or can be established relatively easily. The current work is based on Wikipedias where the mappings between languages are determined by the authors of the articles. We describe a neural-network inspired algorithm which first characterizes each Wikipedia article by a number of keywords, and then considers the identification of word translations as a variant of word alignment in a noisy environment. We present results and evaluations for eight language pairs involving Germanic, Romanic, and Slavic languages as well as Chinese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rapp-etal-2012-identifying">
<titleInfo>
<title>Identifying Word Translations from Comparable Documents Without a Seed Lexicon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The extraction of dictionaries from parallel text corpora is an established technique. However, as parallel corpora are a scarce resource, in recent years the extraction of dictionaries using comparable corpora has obtained increasing attention. In order to find a mapping between languages, almost all approaches suggested in the literature rely on a seed lexicon. The work described here achieves competitive results without requiring such a seed lexicon. Instead it presupposes mappings between comparable documents in different languages. For some common types of textual resources (e.g. encyclopedias or newspaper texts) such mappings are either readily available or can be established relatively easily. The current work is based on Wikipedias where the mappings between languages are determined by the authors of the articles. We describe a neural-network inspired algorithm which first characterizes each Wikipedia article by a number of keywords, and then considers the identification of word translations as a variant of word alignment in a noisy environment. We present results and evaluations for eight language pairs involving Germanic, Romanic, and Slavic languages as well as Chinese.</abstract>
<identifier type="citekey">rapp-etal-2012-identifying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/888_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>460</start>
<end>466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Word Translations from Comparable Documents Without a Seed Lexicon
%A Rapp, Reinhard
%A Sharoff, Serge
%A Babych, Bogdan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F rapp-etal-2012-identifying
%X The extraction of dictionaries from parallel text corpora is an established technique. However, as parallel corpora are a scarce resource, in recent years the extraction of dictionaries using comparable corpora has obtained increasing attention. In order to find a mapping between languages, almost all approaches suggested in the literature rely on a seed lexicon. The work described here achieves competitive results without requiring such a seed lexicon. Instead it presupposes mappings between comparable documents in different languages. For some common types of textual resources (e.g. encyclopedias or newspaper texts) such mappings are either readily available or can be established relatively easily. The current work is based on Wikipedias where the mappings between languages are determined by the authors of the articles. We describe a neural-network inspired algorithm which first characterizes each Wikipedia article by a number of keywords, and then considers the identification of word translations as a variant of word alignment in a noisy environment. We present results and evaluations for eight language pairs involving Germanic, Romanic, and Slavic languages as well as Chinese.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/888_Paper.pdf
%P 460-466
Markdown (Informal)
[Identifying Word Translations from Comparable Documents Without a Seed Lexicon](http://www.lrec-conf.org/proceedings/lrec2012/pdf/888_Paper.pdf) (Rapp et al., LREC 2012)
ACL