@inproceedings{pajzs-etal-2014-media,
title = "Media monitoring and information extraction for the highly inflected agglutinative language {H}ungarian",
author = "Pajzs, J{\'u}lia and
Steinberger, Ralf and
Ehrmann, Maud and
Ebrahim, Mohamed and
Della Rocca, Leonida and
Bucci, Stefano and
Simon, Eszter and
V{\'a}radi, Tam{\'a}s",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/449_Paper.pdf",
pages = "2049--2056",
abstract = "The Europe Media Monitor (EMM) is a fully-automatic system that analyses written online news by gathering articles in over 70 languages and by applying text analysis software for currently 21 languages, without using linguistic tools such as parsers, part-of-speech taggers or morphological analysers. In this paper, we describe the effort of adding to EMM Hungarian text mining tools for news gathering; document categorisation; named entity recognition and classification for persons, organisations and locations; name lemmatisation; quotation recognition; and cross-lingual linking of related news clusters. The major challenge of dealing with the Hungarian language is its high degree of inflection and agglutination. We present several experiments where we apply linguistically light-weight methods to deal with inflection and we propose a method to overcome the challenges. We also present detailed frequency lists of Hungarian person and location name suffixes, as found in real-life news texts. This empirical data can be used to draw further conclusions and to improve existing Named Entity Recognition software. Within EMM, the solutions described here will also be applied to other morphologically complex languages such as those of the Slavic language family. The media monitoring and analysis system EMM is freely accessible online via the web page \url{http://emm.newsbrief.eu/overview.html}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pajzs-etal-2014-media">
<titleInfo>
<title>Media monitoring and information extraction for the highly inflected agglutinative language Hungarian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Júlia</namePart>
<namePart type="family">Pajzs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maud</namePart>
<namePart type="family">Ehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Ebrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonida</namePart>
<namePart type="family">Della Rocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Bucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eszter</namePart>
<namePart type="family">Simon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Váradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Europe Media Monitor (EMM) is a fully-automatic system that analyses written online news by gathering articles in over 70 languages and by applying text analysis software for currently 21 languages, without using linguistic tools such as parsers, part-of-speech taggers or morphological analysers. In this paper, we describe the effort of adding to EMM Hungarian text mining tools for news gathering; document categorisation; named entity recognition and classification for persons, organisations and locations; name lemmatisation; quotation recognition; and cross-lingual linking of related news clusters. The major challenge of dealing with the Hungarian language is its high degree of inflection and agglutination. We present several experiments where we apply linguistically light-weight methods to deal with inflection and we propose a method to overcome the challenges. We also present detailed frequency lists of Hungarian person and location name suffixes, as found in real-life news texts. This empirical data can be used to draw further conclusions and to improve existing Named Entity Recognition software. Within EMM, the solutions described here will also be applied to other morphologically complex languages such as those of the Slavic language family. The media monitoring and analysis system EMM is freely accessible online via the web page http://emm.newsbrief.eu/overview.html.</abstract>
<identifier type="citekey">pajzs-etal-2014-media</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/449_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2049</start>
<end>2056</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Media monitoring and information extraction for the highly inflected agglutinative language Hungarian
%A Pajzs, Júlia
%A Steinberger, Ralf
%A Ehrmann, Maud
%A Ebrahim, Mohamed
%A Della Rocca, Leonida
%A Bucci, Stefano
%A Simon, Eszter
%A Váradi, Tamás
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F pajzs-etal-2014-media
%X The Europe Media Monitor (EMM) is a fully-automatic system that analyses written online news by gathering articles in over 70 languages and by applying text analysis software for currently 21 languages, without using linguistic tools such as parsers, part-of-speech taggers or morphological analysers. In this paper, we describe the effort of adding to EMM Hungarian text mining tools for news gathering; document categorisation; named entity recognition and classification for persons, organisations and locations; name lemmatisation; quotation recognition; and cross-lingual linking of related news clusters. The major challenge of dealing with the Hungarian language is its high degree of inflection and agglutination. We present several experiments where we apply linguistically light-weight methods to deal with inflection and we propose a method to overcome the challenges. We also present detailed frequency lists of Hungarian person and location name suffixes, as found in real-life news texts. This empirical data can be used to draw further conclusions and to improve existing Named Entity Recognition software. Within EMM, the solutions described here will also be applied to other morphologically complex languages such as those of the Slavic language family. The media monitoring and analysis system EMM is freely accessible online via the web page http://emm.newsbrief.eu/overview.html.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/449_Paper.pdf
%P 2049-2056
Markdown (Informal)
[Media monitoring and information extraction for the highly inflected agglutinative language Hungarian](http://www.lrec-conf.org/proceedings/lrec2014/pdf/449_Paper.pdf) (Pajzs et al., LREC 2014)
ACL
- Júlia Pajzs, Ralf Steinberger, Maud Ehrmann, Mohamed Ebrahim, Leonida Della Rocca, Stefano Bucci, Eszter Simon, and Tamás Váradi. 2014. Media monitoring and information extraction for the highly inflected agglutinative language Hungarian. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2049–2056, Reykjavik, Iceland. European Language Resources Association (ELRA).