@inproceedings{neudecker-2016-open,
title = "An Open Corpus for Named Entity Recognition in Historic Newspapers",
author = "Neudecker, Clemens",
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/L16-1689",
pages = "4348--4352",
abstract = "The availability of openly available textual datasets ({``}corpora{''}) with highly accurate manual annotations ({``}gold standard{''}) of named entities (e.g. persons, locations, organizations, etc.) is crucial in the training and evaluation of named entity recognition systems. Currently there are only few such datasets available on the web, and even less for texts containing historical spelling variation. The production and subsequent release into the public domain of four such datasets with 100 pages each for the languages Dutch, French, German (including Austrian) as part of the Europeana Newspapers project is expected to contribute to the further development and improvement of named entity recognition systems with a focus on historical content. This paper describes how these datasets were produced, what challenges were encountered in their creation and informs about their final quality and availability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neudecker-2016-open">
<titleInfo>
<title>An Open Corpus for Named Entity Recognition in Historic Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Clemens</namePart>
<namePart type="family">Neudecker</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 availability of openly available textual datasets (“corpora”) with highly accurate manual annotations (“gold standard”) of named entities (e.g. persons, locations, organizations, etc.) is crucial in the training and evaluation of named entity recognition systems. Currently there are only few such datasets available on the web, and even less for texts containing historical spelling variation. The production and subsequent release into the public domain of four such datasets with 100 pages each for the languages Dutch, French, German (including Austrian) as part of the Europeana Newspapers project is expected to contribute to the further development and improvement of named entity recognition systems with a focus on historical content. This paper describes how these datasets were produced, what challenges were encountered in their creation and informs about their final quality and availability.</abstract>
<identifier type="citekey">neudecker-2016-open</identifier>
<location>
<url>https://aclanthology.org/L16-1689</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4348</start>
<end>4352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Open Corpus for Named Entity Recognition in Historic Newspapers
%A Neudecker, Clemens
%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 neudecker-2016-open
%X The availability of openly available textual datasets (“corpora”) with highly accurate manual annotations (“gold standard”) of named entities (e.g. persons, locations, organizations, etc.) is crucial in the training and evaluation of named entity recognition systems. Currently there are only few such datasets available on the web, and even less for texts containing historical spelling variation. The production and subsequent release into the public domain of four such datasets with 100 pages each for the languages Dutch, French, German (including Austrian) as part of the Europeana Newspapers project is expected to contribute to the further development and improvement of named entity recognition systems with a focus on historical content. This paper describes how these datasets were produced, what challenges were encountered in their creation and informs about their final quality and availability.
%U https://aclanthology.org/L16-1689
%P 4348-4352
Markdown (Informal)
[An Open Corpus for Named Entity Recognition in Historic Newspapers](https://aclanthology.org/L16-1689) (Neudecker, LREC 2016)
ACL