@inproceedings{kucuk-etal-2014-named,
title = "Named Entity Recognition on {T}urkish Tweets",
author = {K{\"u}{\c{c}}{\"u}k, Dilek and
Jacquet, Guillaume and
Steinberger, Ralf},
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/380_Paper.pdf",
pages = "450--454",
abstract = "Various recent studies show that the performance of named entity recognition (NER) systems developed for well-formed text types drops significantly when applied to tweets. The only existing study for the highly inflected agglutinative language Turkish reports a drop in F-Measure from 91{\%} to 19{\%} when ported from news articles to tweets. In this study, we present a new named entity-annotated tweet corpus and a detailed analysis of the various tweet-specific linguistic phenomena. We perform comparative NER experiments with a rule-based multilingual NER system adapted to Turkish on three corpora: a news corpus, our new tweet corpus, and another tweet corpus. Based on the analysis and the experimentation results, we suggest system features required to improve NER results for social media like Twitter.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kucuk-etal-2014-named">
<titleInfo>
<title>Named Entity Recognition on Turkish Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Küçük</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Jacquet</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>
<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>Various recent studies show that the performance of named entity recognition (NER) systems developed for well-formed text types drops significantly when applied to tweets. The only existing study for the highly inflected agglutinative language Turkish reports a drop in F-Measure from 91% to 19% when ported from news articles to tweets. In this study, we present a new named entity-annotated tweet corpus and a detailed analysis of the various tweet-specific linguistic phenomena. We perform comparative NER experiments with a rule-based multilingual NER system adapted to Turkish on three corpora: a news corpus, our new tweet corpus, and another tweet corpus. Based on the analysis and the experimentation results, we suggest system features required to improve NER results for social media like Twitter.</abstract>
<identifier type="citekey">kucuk-etal-2014-named</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/380_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>450</start>
<end>454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition on Turkish Tweets
%A Küçük, Dilek
%A Jacquet, Guillaume
%A Steinberger, Ralf
%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 kucuk-etal-2014-named
%X Various recent studies show that the performance of named entity recognition (NER) systems developed for well-formed text types drops significantly when applied to tweets. The only existing study for the highly inflected agglutinative language Turkish reports a drop in F-Measure from 91% to 19% when ported from news articles to tweets. In this study, we present a new named entity-annotated tweet corpus and a detailed analysis of the various tweet-specific linguistic phenomena. We perform comparative NER experiments with a rule-based multilingual NER system adapted to Turkish on three corpora: a news corpus, our new tweet corpus, and another tweet corpus. Based on the analysis and the experimentation results, we suggest system features required to improve NER results for social media like Twitter.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/380_Paper.pdf
%P 450-454
Markdown (Informal)
[Named Entity Recognition on Turkish Tweets](http://www.lrec-conf.org/proceedings/lrec2014/pdf/380_Paper.pdf) (Küçük et al., LREC 2014)
ACL
- Dilek Küçük, Guillaume Jacquet, and Ralf Steinberger. 2014. Named Entity Recognition on Turkish Tweets. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 450–454, Reykjavik, Iceland. European Language Resources Association (ELRA).