@inproceedings{aker-etal-2014-bilingual,
title = "Bilingual dictionaries for all {EU} languages",
author = "Aker, Ahmet and
Paramita, Monica and
Pinnis, M{\=a}rcis and
Gaizauskas, Robert",
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/803_Paper.pdf",
pages = "2839--2845",
abstract = "Bilingual dictionaries can be automatically generated using the GIZA++ tool. However, these dictionaries contain a lot of noise, because of which the quality of outputs of tools relying on the dictionaries are negatively affected. In this work we present three different methods for cleaning noise from automatically generated bilingual dictionaries: LLR, pivot and translation based approach. We have applied these approaches on the GIZA++ dictionaries {--} dictionaries covering official EU languages {--} in order to remove noise. Our evaluation showed that all methods help to reduce noise. However, the best performance is achieved using the transliteration based approach. We provide all bilingual dictionaries (the original GIZA++ dictionaries and the cleaned ones) free for download. We also provide the cleaning tools and scripts for free download.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aker-etal-2014-bilingual">
<titleInfo>
<title>Bilingual dictionaries for all EU languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Aker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Paramita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mārcis</namePart>
<namePart type="family">Pinnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</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 can be automatically generated using the GIZA++ tool. However, these dictionaries contain a lot of noise, because of which the quality of outputs of tools relying on the dictionaries are negatively affected. In this work we present three different methods for cleaning noise from automatically generated bilingual dictionaries: LLR, pivot and translation based approach. We have applied these approaches on the GIZA++ dictionaries – dictionaries covering official EU languages – in order to remove noise. Our evaluation showed that all methods help to reduce noise. However, the best performance is achieved using the transliteration based approach. We provide all bilingual dictionaries (the original GIZA++ dictionaries and the cleaned ones) free for download. We also provide the cleaning tools and scripts for free download.</abstract>
<identifier type="citekey">aker-etal-2014-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/803_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2839</start>
<end>2845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual dictionaries for all EU languages
%A Aker, Ahmet
%A Paramita, Monica
%A Pinnis, Mārcis
%A Gaizauskas, Robert
%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 aker-etal-2014-bilingual
%X Bilingual dictionaries can be automatically generated using the GIZA++ tool. However, these dictionaries contain a lot of noise, because of which the quality of outputs of tools relying on the dictionaries are negatively affected. In this work we present three different methods for cleaning noise from automatically generated bilingual dictionaries: LLR, pivot and translation based approach. We have applied these approaches on the GIZA++ dictionaries – dictionaries covering official EU languages – in order to remove noise. Our evaluation showed that all methods help to reduce noise. However, the best performance is achieved using the transliteration based approach. We provide all bilingual dictionaries (the original GIZA++ dictionaries and the cleaned ones) free for download. We also provide the cleaning tools and scripts for free download.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/803_Paper.pdf
%P 2839-2845
Markdown (Informal)
[Bilingual dictionaries for all EU languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/803_Paper.pdf) (Aker et al., LREC 2014)
ACL
- Ahmet Aker, Monica Paramita, Mārcis Pinnis, and Robert Gaizauskas. 2014. Bilingual dictionaries for all EU languages. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2839–2845, Reykjavik, Iceland. European Language Resources Association (ELRA).