@inproceedings{charton-torres-moreno-2010-nlgbase,
title = "{NLG}b{A}se: A Free Linguistic Resource for Natural Language Processing Systems",
author = "Charton, Eric and
Torres-Moreno, Juan-Manuel",
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/900_Paper.pdf",
abstract = "Availability of labeled language resources, such as annotated corpora and domain dependent labeled language resources is crucial for experiments in the field of Natural Language Processing. Most often, due to lack of resources, manual verification and annotation of electronic text material is a prerequisite for the development of NLP tools. In the context of under-resourced language, the lack of copora becomes a crucial problem because most of the research efforts are supported by organizations with limited funds. Using free, multilingual and highly structured corpora like Wikipedia to produce automatically labeled language resources can be an answer to those needs. This paper introduces NLGbAse, a multilingual linguistic resource built from the Wikipedia encyclopedic content. This system produces structured metadata which make possible the automatic annotation of corpora with syntactical and semantical labels. A metadata contains semantical and statistical informations related to an encyclopedic document. To validate our approach, we built and evaluated a Named Entity Recognition tool, trained with Wikipedia corpora annotated by our system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="charton-torres-moreno-2010-nlgbase">
<titleInfo>
<title>NLGbAse: A Free Linguistic Resource for Natural Language Processing Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Charton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan-Manuel</namePart>
<namePart type="family">Torres-Moreno</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>Availability of labeled language resources, such as annotated corpora and domain dependent labeled language resources is crucial for experiments in the field of Natural Language Processing. Most often, due to lack of resources, manual verification and annotation of electronic text material is a prerequisite for the development of NLP tools. In the context of under-resourced language, the lack of copora becomes a crucial problem because most of the research efforts are supported by organizations with limited funds. Using free, multilingual and highly structured corpora like Wikipedia to produce automatically labeled language resources can be an answer to those needs. This paper introduces NLGbAse, a multilingual linguistic resource built from the Wikipedia encyclopedic content. This system produces structured metadata which make possible the automatic annotation of corpora with syntactical and semantical labels. A metadata contains semantical and statistical informations related to an encyclopedic document. To validate our approach, we built and evaluated a Named Entity Recognition tool, trained with Wikipedia corpora annotated by our system.</abstract>
<identifier type="citekey">charton-torres-moreno-2010-nlgbase</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/900_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLGbAse: A Free Linguistic Resource for Natural Language Processing Systems
%A Charton, Eric
%A Torres-Moreno, Juan-Manuel
%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 charton-torres-moreno-2010-nlgbase
%X Availability of labeled language resources, such as annotated corpora and domain dependent labeled language resources is crucial for experiments in the field of Natural Language Processing. Most often, due to lack of resources, manual verification and annotation of electronic text material is a prerequisite for the development of NLP tools. In the context of under-resourced language, the lack of copora becomes a crucial problem because most of the research efforts are supported by organizations with limited funds. Using free, multilingual and highly structured corpora like Wikipedia to produce automatically labeled language resources can be an answer to those needs. This paper introduces NLGbAse, a multilingual linguistic resource built from the Wikipedia encyclopedic content. This system produces structured metadata which make possible the automatic annotation of corpora with syntactical and semantical labels. A metadata contains semantical and statistical informations related to an encyclopedic document. To validate our approach, we built and evaluated a Named Entity Recognition tool, trained with Wikipedia corpora annotated by our system.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/900_Paper.pdf
Markdown (Informal)
[NLGbAse: A Free Linguistic Resource for Natural Language Processing Systems](http://www.lrec-conf.org/proceedings/lrec2010/pdf/900_Paper.pdf) (Charton & Torres-Moreno, LREC 2010)
ACL