@inproceedings{goldhahn-etal-2012-building,
title = "Building Large Monolingual Dictionaries at the {L}eipzig Corpora Collection: From 100 to 200 Languages",
author = "Goldhahn, Dirk and
Eckart, Thomas and
Quasthoff, Uwe",
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/327_Paper.pdf",
pages = "759--765",
abstract = "The Leipzig Corpora Collection offers free online access to 136 monolingual dictionaries enriched with statistical information. In this paper we describe current advances of the project in collecting and processing text data automatically for a large number of languages. Our main interest lies in languages of low density, where only few text data exists online. The aim of this approach is to create monolingual dictionaries and statistical information for a high number of new languages and to expand the existing dictionaries, opening up new possibilities for linguistic typology and other research. Focus of this paper will be set on the infrastructure for the automatic acquisition of large amounts of monolingual text in many languages from various sources. Preliminary results of the collection of text data will be presented. The mainly language-independent framework for preprocessing, cleaning and creating the corpora and computing the necessary statistics will also be depicted.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldhahn-etal-2012-building">
<titleInfo>
<title>Building Large Monolingual Dictionaries at the Leipzig Corpora Collection: From 100 to 200 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Goldhahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Eckart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Quasthoff</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 Leipzig Corpora Collection offers free online access to 136 monolingual dictionaries enriched with statistical information. In this paper we describe current advances of the project in collecting and processing text data automatically for a large number of languages. Our main interest lies in languages of low density, where only few text data exists online. The aim of this approach is to create monolingual dictionaries and statistical information for a high number of new languages and to expand the existing dictionaries, opening up new possibilities for linguistic typology and other research. Focus of this paper will be set on the infrastructure for the automatic acquisition of large amounts of monolingual text in many languages from various sources. Preliminary results of the collection of text data will be presented. The mainly language-independent framework for preprocessing, cleaning and creating the corpora and computing the necessary statistics will also be depicted.</abstract>
<identifier type="citekey">goldhahn-etal-2012-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/327_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>759</start>
<end>765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Large Monolingual Dictionaries at the Leipzig Corpora Collection: From 100 to 200 Languages
%A Goldhahn, Dirk
%A Eckart, Thomas
%A Quasthoff, Uwe
%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 goldhahn-etal-2012-building
%X The Leipzig Corpora Collection offers free online access to 136 monolingual dictionaries enriched with statistical information. In this paper we describe current advances of the project in collecting and processing text data automatically for a large number of languages. Our main interest lies in languages of low density, where only few text data exists online. The aim of this approach is to create monolingual dictionaries and statistical information for a high number of new languages and to expand the existing dictionaries, opening up new possibilities for linguistic typology and other research. Focus of this paper will be set on the infrastructure for the automatic acquisition of large amounts of monolingual text in many languages from various sources. Preliminary results of the collection of text data will be presented. The mainly language-independent framework for preprocessing, cleaning and creating the corpora and computing the necessary statistics will also be depicted.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/327_Paper.pdf
%P 759-765
Markdown (Informal)
[Building Large Monolingual Dictionaries at the Leipzig Corpora Collection: From 100 to 200 Languages](http://www.lrec-conf.org/proceedings/lrec2012/pdf/327_Paper.pdf) (Goldhahn et al., LREC 2012)
ACL