@inproceedings{cassidy-2016-publishing,
title = "Publishing the Trove Newspaper Corpus",
author = "Cassidy, Steve",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1715",
pages = "4520--4525",
abstract = "The Trove Newspaper Corpus is derived from the National Library of Australia{'}s digital archive of newspaper text. The corpus is a snapshot of the NLA collection taken in 2015 to be made available for language research as part of the Alveo Virtual Laboratory and contains 143 million articles dating from 1806 to 2007. This paper describes the work we have done to make this large corpus available as a research collection, facilitating access to individual documents and enabling large scale processing of the newspaper text in a cloud-based environment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cassidy-2016-publishing">
<titleInfo>
<title>Publishing the Trove Newspaper Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Cassidy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Trove Newspaper Corpus is derived from the National Library of Australia’s digital archive of newspaper text. The corpus is a snapshot of the NLA collection taken in 2015 to be made available for language research as part of the Alveo Virtual Laboratory and contains 143 million articles dating from 1806 to 2007. This paper describes the work we have done to make this large corpus available as a research collection, facilitating access to individual documents and enabling large scale processing of the newspaper text in a cloud-based environment.</abstract>
<identifier type="citekey">cassidy-2016-publishing</identifier>
<location>
<url>https://aclanthology.org/L16-1715</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4520</start>
<end>4525</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Publishing the Trove Newspaper Corpus
%A Cassidy, Steve
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F cassidy-2016-publishing
%X The Trove Newspaper Corpus is derived from the National Library of Australia’s digital archive of newspaper text. The corpus is a snapshot of the NLA collection taken in 2015 to be made available for language research as part of the Alveo Virtual Laboratory and contains 143 million articles dating from 1806 to 2007. This paper describes the work we have done to make this large corpus available as a research collection, facilitating access to individual documents and enabling large scale processing of the newspaper text in a cloud-based environment.
%U https://aclanthology.org/L16-1715
%P 4520-4525
Markdown (Informal)
[Publishing the Trove Newspaper Corpus](https://aclanthology.org/L16-1715) (Cassidy, LREC 2016)
ACL
- Steve Cassidy. 2016. Publishing the Trove Newspaper Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4520–4525, Portorož, Slovenia. European Language Resources Association (ELRA).