@inproceedings{eckart-etal-2014-500,
title = "A 500 Million Word {POS}-Tagged {I}celandic Corpus",
author = "Eckart, Thomas and
Hallsteinsd{\'o}ttir, Erla and
Helgad{\'o}ttir, Sigr{\'u}n and
Quasthoff, Uwe and
Goldhahn, Dirk",
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/852_Paper.pdf",
pages = "2398--2402",
abstract = "The new POS-tagged Icelandic corpus of the Leipzig Corpora Collection is an extensive resource for the analysis of the Icelandic language. As it contains a large share of all Web documents hosted under the .is top-level domain, it is especially valuable for investigations on modern Icelandic and non-standard language varieties. The corpus is accessible via a dedicated web portal and large shares are available for download. Focus of this paper will be the description of the tagging process and evaluation of statistical properties like word form frequencies and part of speech tag distributions. The latter will be in particular compared with values from the Icelandic Frequency Dictionary (IFD) Corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eckart-etal-2014-500">
<titleInfo>
<title>A 500 Million Word POS-Tagged Icelandic Corpus</title>
</titleInfo>
<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">Erla</namePart>
<namePart type="family">Hallsteinsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sigrún</namePart>
<namePart type="family">Helgadóttir</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>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Goldhahn</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>The new POS-tagged Icelandic corpus of the Leipzig Corpora Collection is an extensive resource for the analysis of the Icelandic language. As it contains a large share of all Web documents hosted under the .is top-level domain, it is especially valuable for investigations on modern Icelandic and non-standard language varieties. The corpus is accessible via a dedicated web portal and large shares are available for download. Focus of this paper will be the description of the tagging process and evaluation of statistical properties like word form frequencies and part of speech tag distributions. The latter will be in particular compared with values from the Icelandic Frequency Dictionary (IFD) Corpus.</abstract>
<identifier type="citekey">eckart-etal-2014-500</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/852_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2398</start>
<end>2402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A 500 Million Word POS-Tagged Icelandic Corpus
%A Eckart, Thomas
%A Hallsteinsdóttir, Erla
%A Helgadóttir, Sigrún
%A Quasthoff, Uwe
%A Goldhahn, Dirk
%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 eckart-etal-2014-500
%X The new POS-tagged Icelandic corpus of the Leipzig Corpora Collection is an extensive resource for the analysis of the Icelandic language. As it contains a large share of all Web documents hosted under the .is top-level domain, it is especially valuable for investigations on modern Icelandic and non-standard language varieties. The corpus is accessible via a dedicated web portal and large shares are available for download. Focus of this paper will be the description of the tagging process and evaluation of statistical properties like word form frequencies and part of speech tag distributions. The latter will be in particular compared with values from the Icelandic Frequency Dictionary (IFD) Corpus.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/852_Paper.pdf
%P 2398-2402
Markdown (Informal)
[A 500 Million Word POS-Tagged Icelandic Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/852_Paper.pdf) (Eckart et al., LREC 2014)
ACL
- Thomas Eckart, Erla Hallsteinsdóttir, Sigrún Helgadóttir, Uwe Quasthoff, and Dirk Goldhahn. 2014. A 500 Million Word POS-Tagged Icelandic Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2398–2402, Reykjavik, Iceland. European Language Resources Association (ELRA).