@inproceedings{desmet-hoste-2010-towards,
title = "Towards a Balanced Named Entity Corpus for {D}utch",
author = "Desmet, Bart and
Hoste, V{\'e}ronique",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/210_Paper.pdf",
abstract = "This paper introduces a new named entity corpus for Dutch. State-of-the-art named entity recognition systems require a substantial annotated corpus to be trained on. Such corpora exist for English, but not for Dutch. The STEVIN-funded SoNaR project aims to produce a diverse 500-million-word reference corpus of written Dutch, with four semantic annotation layers: named entities, coreference relations, semantic roles and spatiotemporal expressions. A 1-million-word subset will be manually corrected. Named entity annotation guidelines for Dutch were developed, adapted from the MUC and ACE guidelines. Adaptations include the annotation of products and events, the classification into subtypes, and the markup of metonymic usage. Inter-annotator agreement experiments were conducted to corroborate the reliability of the guidelines, which yielded satisfactory results (Kappa scores above 0.90). We are building a NER system, trained on the 1-million-word subcorpus, to automatically classify the remainder of the SoNaR corpus. To this end, experiments with various classification algorithms (MBL, SVM, CRF) and features have been carried out and evaluated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="desmet-hoste-2010-towards">
<titleInfo>
<title>Towards a Balanced Named Entity Corpus for Dutch</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a new named entity corpus for Dutch. State-of-the-art named entity recognition systems require a substantial annotated corpus to be trained on. Such corpora exist for English, but not for Dutch. The STEVIN-funded SoNaR project aims to produce a diverse 500-million-word reference corpus of written Dutch, with four semantic annotation layers: named entities, coreference relations, semantic roles and spatiotemporal expressions. A 1-million-word subset will be manually corrected. Named entity annotation guidelines for Dutch were developed, adapted from the MUC and ACE guidelines. Adaptations include the annotation of products and events, the classification into subtypes, and the markup of metonymic usage. Inter-annotator agreement experiments were conducted to corroborate the reliability of the guidelines, which yielded satisfactory results (Kappa scores above 0.90). We are building a NER system, trained on the 1-million-word subcorpus, to automatically classify the remainder of the SoNaR corpus. To this end, experiments with various classification algorithms (MBL, SVM, CRF) and features have been carried out and evaluated.</abstract>
<identifier type="citekey">desmet-hoste-2010-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/210_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Balanced Named Entity Corpus for Dutch
%A Desmet, Bart
%A Hoste, Véronique
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F desmet-hoste-2010-towards
%X This paper introduces a new named entity corpus for Dutch. State-of-the-art named entity recognition systems require a substantial annotated corpus to be trained on. Such corpora exist for English, but not for Dutch. The STEVIN-funded SoNaR project aims to produce a diverse 500-million-word reference corpus of written Dutch, with four semantic annotation layers: named entities, coreference relations, semantic roles and spatiotemporal expressions. A 1-million-word subset will be manually corrected. Named entity annotation guidelines for Dutch were developed, adapted from the MUC and ACE guidelines. Adaptations include the annotation of products and events, the classification into subtypes, and the markup of metonymic usage. Inter-annotator agreement experiments were conducted to corroborate the reliability of the guidelines, which yielded satisfactory results (Kappa scores above 0.90). We are building a NER system, trained on the 1-million-word subcorpus, to automatically classify the remainder of the SoNaR corpus. To this end, experiments with various classification algorithms (MBL, SVM, CRF) and features have been carried out and evaluated.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/210_Paper.pdf
Markdown (Informal)
[Towards a Balanced Named Entity Corpus for Dutch](http://www.lrec-conf.org/proceedings/lrec2010/pdf/210_Paper.pdf) (Desmet & Hoste, LREC 2010)
ACL
- Bart Desmet and Véronique Hoste. 2010. Towards a Balanced Named Entity Corpus for Dutch. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).