@inproceedings{helgadottir-etal-2014-correcting,
title = "Correcting Errors in a New Gold Standard for Tagging {I}celandic Text",
author = {Helgad{\'o}ttir, Sigr{\'u}n and
Loftsson, Hrafn and
R{\"o}gnvaldsson, Eir{\'\i}kur},
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/677_Paper.pdf",
pages = "2944--2948",
abstract = "In this paper, we describe the correction of PoS tags in a new Icelandic corpus, MIM-GOLD, consisting of about 1 million tokens sampled from the Tagged Icelandic Corpus, M{\'I}M, released in 2013. The goal is to use the corpus, among other things, as a new gold standard for training and testing PoS taggers. The construction of the corpus was first described in 2010 together with preliminary work on error detection and correction. In this paper, we describe further the correction of tags in the corpus. We describe manual correction and a method for semi-automatic error detection and correction. We show that, even after manual correction, the number of tagging errors in the corpus can be reduced significantly by applying our semi-automatic detection and correction method. After the semi-automatic error correction, preliminary evaluation of tagging accuracy shows very low error rates. We hope that the existence of the corpus will make it possible to improve PoS taggers for Icelandic text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="helgadottir-etal-2014-correcting">
<titleInfo>
<title>Correcting Errors in a New Gold Standard for Tagging Icelandic Text</title>
</titleInfo>
<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">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiríkur</namePart>
<namePart type="family">Rögnvaldsson</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>In this paper, we describe the correction of PoS tags in a new Icelandic corpus, MIM-GOLD, consisting of about 1 million tokens sampled from the Tagged Icelandic Corpus, MÍM, released in 2013. The goal is to use the corpus, among other things, as a new gold standard for training and testing PoS taggers. The construction of the corpus was first described in 2010 together with preliminary work on error detection and correction. In this paper, we describe further the correction of tags in the corpus. We describe manual correction and a method for semi-automatic error detection and correction. We show that, even after manual correction, the number of tagging errors in the corpus can be reduced significantly by applying our semi-automatic detection and correction method. After the semi-automatic error correction, preliminary evaluation of tagging accuracy shows very low error rates. We hope that the existence of the corpus will make it possible to improve PoS taggers for Icelandic text.</abstract>
<identifier type="citekey">helgadottir-etal-2014-correcting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/677_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2944</start>
<end>2948</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correcting Errors in a New Gold Standard for Tagging Icelandic Text
%A Helgadóttir, Sigrún
%A Loftsson, Hrafn
%A Rögnvaldsson, Eiríkur
%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 helgadottir-etal-2014-correcting
%X In this paper, we describe the correction of PoS tags in a new Icelandic corpus, MIM-GOLD, consisting of about 1 million tokens sampled from the Tagged Icelandic Corpus, MÍM, released in 2013. The goal is to use the corpus, among other things, as a new gold standard for training and testing PoS taggers. The construction of the corpus was first described in 2010 together with preliminary work on error detection and correction. In this paper, we describe further the correction of tags in the corpus. We describe manual correction and a method for semi-automatic error detection and correction. We show that, even after manual correction, the number of tagging errors in the corpus can be reduced significantly by applying our semi-automatic detection and correction method. After the semi-automatic error correction, preliminary evaluation of tagging accuracy shows very low error rates. We hope that the existence of the corpus will make it possible to improve PoS taggers for Icelandic text.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/677_Paper.pdf
%P 2944-2948
Markdown (Informal)
[Correcting Errors in a New Gold Standard for Tagging Icelandic Text](http://www.lrec-conf.org/proceedings/lrec2014/pdf/677_Paper.pdf) (Helgadóttir et al., LREC 2014)
ACL