@inproceedings{fromreide-etal-2014-crowdsourcing,
title = "Crowdsourcing and annotating {NER} for {T}witter {\#}drift",
author = "Fromreide, Hege and
Hovy, Dirk and
S{\o}gaard, Anders",
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/421_Paper.pdf",
pages = "2544--2547",
abstract = "We present two new NER datasets for Twitter; a manually annotated set of 1,467 tweets (kappa=0.942) and a set of 2,975 expert-corrected, crowdsourced NER annotated tweets from the dataset described in Finin et al. (2010). In our experiments with these datasets, we observe two important points: (a) language drift on Twitter is significant, and while off-the-shelf systems have been reported to perform well on in-sample data, they often perform poorly on new samples of tweets, (b) state-of-the-art performance across various datasets can be obtained from crowdsourced annotations, making it more feasible to {``}catch up{''} with language drift.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fromreide-etal-2014-crowdsourcing">
<titleInfo>
<title>Crowdsourcing and annotating NER for Twitter #drift</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hege</namePart>
<namePart type="family">Fromreide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</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>We present two new NER datasets for Twitter; a manually annotated set of 1,467 tweets (kappa=0.942) and a set of 2,975 expert-corrected, crowdsourced NER annotated tweets from the dataset described in Finin et al. (2010). In our experiments with these datasets, we observe two important points: (a) language drift on Twitter is significant, and while off-the-shelf systems have been reported to perform well on in-sample data, they often perform poorly on new samples of tweets, (b) state-of-the-art performance across various datasets can be obtained from crowdsourced annotations, making it more feasible to “catch up” with language drift.</abstract>
<identifier type="citekey">fromreide-etal-2014-crowdsourcing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/421_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2544</start>
<end>2547</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crowdsourcing and annotating NER for Twitter #drift
%A Fromreide, Hege
%A Hovy, Dirk
%A Søgaard, Anders
%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 fromreide-etal-2014-crowdsourcing
%X We present two new NER datasets for Twitter; a manually annotated set of 1,467 tweets (kappa=0.942) and a set of 2,975 expert-corrected, crowdsourced NER annotated tweets from the dataset described in Finin et al. (2010). In our experiments with these datasets, we observe two important points: (a) language drift on Twitter is significant, and while off-the-shelf systems have been reported to perform well on in-sample data, they often perform poorly on new samples of tweets, (b) state-of-the-art performance across various datasets can be obtained from crowdsourced annotations, making it more feasible to “catch up” with language drift.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/421_Paper.pdf
%P 2544-2547
Markdown (Informal)
[Crowdsourcing and annotating NER for Twitter #drift](http://www.lrec-conf.org/proceedings/lrec2014/pdf/421_Paper.pdf) (Fromreide et al., LREC 2014)
ACL
- Hege Fromreide, Dirk Hovy, and Anders Søgaard. 2014. Crowdsourcing and annotating NER for Twitter #drift. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2544–2547, Reykjavik, Iceland. European Language Resources Association (ELRA).