@inproceedings{melero-etal-2012-holaaa,
title = "Holaaa!! writin like u talk is kewl but kinda hard 4 {NLP}",
author = "Melero, Maite and
Costa-Juss{\`a}, Marta R. and
Domingo, Judith and
Marquina, Montse and
Quixal, Mart{\'\i}",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/627_Paper.pdf",
pages = "3794--3800",
abstract = "We present work in progress aiming to build tools for the normalization of User-Generated Content (UGC). As we will see, the task requires the revisiting of the initial steps of NLP processing, since UGC (micro-blog, blog, and, generally, Web 2.0 user texts) presents a number of non-standard communicative and linguistic characteristics, and is in fact much closer to oral and colloquial language than to edited text. We present and characterize a corpus of UGC text in Spanish from three different sources: Twitter, consumer reviews and blogs. We motivate the need for UGC text normalization by analyzing the problems found when processing this type of text through a conventional language processing pipeline, particularly in the tasks of lemmatization and morphosyntactic tagging, and finally we propose a strategy for automatically normalizing UGC using a selector of correct forms on top of a pre-existing spell-checker.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="melero-etal-2012-holaaa">
<titleInfo>
<title>Holaaa!! writin like u talk is kewl but kinda hard 4 NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-Jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Domingo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Montse</namePart>
<namePart type="family">Marquina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martí</namePart>
<namePart type="family">Quixal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present work in progress aiming to build tools for the normalization of User-Generated Content (UGC). As we will see, the task requires the revisiting of the initial steps of NLP processing, since UGC (micro-blog, blog, and, generally, Web 2.0 user texts) presents a number of non-standard communicative and linguistic characteristics, and is in fact much closer to oral and colloquial language than to edited text. We present and characterize a corpus of UGC text in Spanish from three different sources: Twitter, consumer reviews and blogs. We motivate the need for UGC text normalization by analyzing the problems found when processing this type of text through a conventional language processing pipeline, particularly in the tasks of lemmatization and morphosyntactic tagging, and finally we propose a strategy for automatically normalizing UGC using a selector of correct forms on top of a pre-existing spell-checker.</abstract>
<identifier type="citekey">melero-etal-2012-holaaa</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/627_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3794</start>
<end>3800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Holaaa!! writin like u talk is kewl but kinda hard 4 NLP
%A Melero, Maite
%A Costa-Jussà, Marta R.
%A Domingo, Judith
%A Marquina, Montse
%A Quixal, Martí
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F melero-etal-2012-holaaa
%X We present work in progress aiming to build tools for the normalization of User-Generated Content (UGC). As we will see, the task requires the revisiting of the initial steps of NLP processing, since UGC (micro-blog, blog, and, generally, Web 2.0 user texts) presents a number of non-standard communicative and linguistic characteristics, and is in fact much closer to oral and colloquial language than to edited text. We present and characterize a corpus of UGC text in Spanish from three different sources: Twitter, consumer reviews and blogs. We motivate the need for UGC text normalization by analyzing the problems found when processing this type of text through a conventional language processing pipeline, particularly in the tasks of lemmatization and morphosyntactic tagging, and finally we propose a strategy for automatically normalizing UGC using a selector of correct forms on top of a pre-existing spell-checker.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/627_Paper.pdf
%P 3794-3800
Markdown (Informal)
[Holaaa!! writin like u talk is kewl but kinda hard 4 NLP](http://www.lrec-conf.org/proceedings/lrec2012/pdf/627_Paper.pdf) (Melero et al., LREC 2012)
ACL
- Maite Melero, Marta R. Costa-Jussà, Judith Domingo, Montse Marquina, and Martí Quixal. 2012. Holaaa!! writin like u talk is kewl but kinda hard 4 NLP. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3794–3800, Istanbul, Turkey. European Language Resources Association (ELRA).