@inproceedings{de-clercq-etal-2014-towards,
title = "Towards Shared Datasets for Normalization Research",
author = "De Clercq, Orph{\'e}e and
Schulz, Sarah and
Desmet, Bart and
Hoste, V{\'e}ronique",
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/733_Paper.pdf",
pages = "1218--1223",
abstract = "In this paper we present a Dutch and English dataset that can serve as a gold standard for evaluating text normalization approaches. With the combination of text messages, message board posts and tweets, these datasets represent a variety of user generated content. All data was manually normalized to their standard form using newly-developed guidelines. We perform automatic lexical normalization experiments on these datasets using statistical machine translation techniques. We focus on both the word and character level and find that we can improve the BLEU score with ca. 20{\%} for both languages. In order for this user generated content data to be released publicly to the research community some issues first need to be resolved. These are discussed in closer detail by focussing on the current legislation and by investigating previous similar data collection projects. With this discussion we hope to shed some light on various difficulties researchers are facing when trying to share social media data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-clercq-etal-2014-towards">
<titleInfo>
<title>Towards Shared Datasets for Normalization Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>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>In this paper we present a Dutch and English dataset that can serve as a gold standard for evaluating text normalization approaches. With the combination of text messages, message board posts and tweets, these datasets represent a variety of user generated content. All data was manually normalized to their standard form using newly-developed guidelines. We perform automatic lexical normalization experiments on these datasets using statistical machine translation techniques. We focus on both the word and character level and find that we can improve the BLEU score with ca. 20% for both languages. In order for this user generated content data to be released publicly to the research community some issues first need to be resolved. These are discussed in closer detail by focussing on the current legislation and by investigating previous similar data collection projects. With this discussion we hope to shed some light on various difficulties researchers are facing when trying to share social media data.</abstract>
<identifier type="citekey">de-clercq-etal-2014-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/733_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1218</start>
<end>1223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Shared Datasets for Normalization Research
%A De Clercq, Orphée
%A Schulz, Sarah
%A Desmet, Bart
%A Hoste, Véronique
%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 de-clercq-etal-2014-towards
%X In this paper we present a Dutch and English dataset that can serve as a gold standard for evaluating text normalization approaches. With the combination of text messages, message board posts and tweets, these datasets represent a variety of user generated content. All data was manually normalized to their standard form using newly-developed guidelines. We perform automatic lexical normalization experiments on these datasets using statistical machine translation techniques. We focus on both the word and character level and find that we can improve the BLEU score with ca. 20% for both languages. In order for this user generated content data to be released publicly to the research community some issues first need to be resolved. These are discussed in closer detail by focussing on the current legislation and by investigating previous similar data collection projects. With this discussion we hope to shed some light on various difficulties researchers are facing when trying to share social media data.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/733_Paper.pdf
%P 1218-1223
Markdown (Informal)
[Towards Shared Datasets for Normalization Research](http://www.lrec-conf.org/proceedings/lrec2014/pdf/733_Paper.pdf) (De Clercq et al., LREC 2014)
ACL
- Orphée De Clercq, Sarah Schulz, Bart Desmet, and Véronique Hoste. 2014. Towards Shared Datasets for Normalization Research. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1218–1223, Reykjavik, Iceland. European Language Resources Association (ELRA).