@inproceedings{steingrimsson-etal-2020-facilitating,
title = "Facilitating Corpus Usage: Making {I}celandic Corpora More Accessible for Researchers and Language Users",
author = {Steingr{\'\i}msson, Stein{\th}{\'o}r and
Barkarson, Starka{\dh}ur and
{\"O}rn{\'o}lfsson, Gunnar Thor},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.416",
pages = "3399--3405",
abstract = "We introduce an array of open and accessible tools to facilitate the use of the Icelandic Gigaword Corpus, in the field of Natural Language Processing as well as for students, linguists, sociologists and others benefitting from using large corpora. A KWIC engine, powered by the Swedish Korp tool is adapted to the specifics of the corpus. An n-gram viewer, highly customizable to suit different needs, allows users to study word usage throughout the period of our text collection. A frequency dictionary provides much sought after information about word frequency statistics, computed for each subcorpus as well as aggregate, disambiguating homographs based on their respective lemmas and morphosyntactic tags. Furthermore, we provide n-grams based on the corpus, and a variety of pre-trained word embeddings models, based on word2vec, GloVe, fastText and ELMo. For three of the model types, multiple word embedding models are available trained with different algorithms and using either lemmatised or unlemmatised texts.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steingrimsson-etal-2020-facilitating">
<titleInfo>
<title>Facilitating Corpus Usage: Making Icelandic Corpora More Accessible for Researchers and Language Users</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stein\thór</namePart>
<namePart type="family">Steingrímsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Starka\dhur</namePart>
<namePart type="family">Barkarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunnar</namePart>
<namePart type="given">Thor</namePart>
<namePart type="family">Örnólfsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce an array of open and accessible tools to facilitate the use of the Icelandic Gigaword Corpus, in the field of Natural Language Processing as well as for students, linguists, sociologists and others benefitting from using large corpora. A KWIC engine, powered by the Swedish Korp tool is adapted to the specifics of the corpus. An n-gram viewer, highly customizable to suit different needs, allows users to study word usage throughout the period of our text collection. A frequency dictionary provides much sought after information about word frequency statistics, computed for each subcorpus as well as aggregate, disambiguating homographs based on their respective lemmas and morphosyntactic tags. Furthermore, we provide n-grams based on the corpus, and a variety of pre-trained word embeddings models, based on word2vec, GloVe, fastText and ELMo. For three of the model types, multiple word embedding models are available trained with different algorithms and using either lemmatised or unlemmatised texts.</abstract>
<identifier type="citekey">steingrimsson-etal-2020-facilitating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.416</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3399</start>
<end>3405</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Facilitating Corpus Usage: Making Icelandic Corpora More Accessible for Researchers and Language Users
%A Steingrímsson, Stein\thór
%A Barkarson, Starka\dhur
%A Örnólfsson, Gunnar Thor
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F steingrimsson-etal-2020-facilitating
%X We introduce an array of open and accessible tools to facilitate the use of the Icelandic Gigaword Corpus, in the field of Natural Language Processing as well as for students, linguists, sociologists and others benefitting from using large corpora. A KWIC engine, powered by the Swedish Korp tool is adapted to the specifics of the corpus. An n-gram viewer, highly customizable to suit different needs, allows users to study word usage throughout the period of our text collection. A frequency dictionary provides much sought after information about word frequency statistics, computed for each subcorpus as well as aggregate, disambiguating homographs based on their respective lemmas and morphosyntactic tags. Furthermore, we provide n-grams based on the corpus, and a variety of pre-trained word embeddings models, based on word2vec, GloVe, fastText and ELMo. For three of the model types, multiple word embedding models are available trained with different algorithms and using either lemmatised or unlemmatised texts.
%U https://aclanthology.org/2020.lrec-1.416
%P 3399-3405
Markdown (Informal)
[Facilitating Corpus Usage: Making Icelandic Corpora More Accessible for Researchers and Language Users](https://aclanthology.org/2020.lrec-1.416) (Steingrímsson et al., LREC 2020)
ACL