@inproceedings{van-der-goot-etal-2020-norm,
title = "Norm It! Lexical Normalization for {I}talian and Its Downstream Effects for Dependency Parsing",
author = "van der Goot, Rob and
Ramponi, Alan and
Caselli, Tommaso and
Cafagna, Michele and
De Mattei, Lorenzo",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.769",
pages = "6272--6278",
abstract = "Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen{'}s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: \url{http://bitbucket.org/robvanderg/normit}.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-der-goot-etal-2020-norm">
<titleInfo>
<title>Norm It! Lexical Normalization for Italian and Its Downstream Effects for Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ramponi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Cafagna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">De Mattei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen’s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.</abstract>
<identifier type="citekey">van-der-goot-etal-2020-norm</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.769</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6272</start>
<end>6278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Norm It! Lexical Normalization for Italian and Its Downstream Effects for Dependency Parsing
%A van der Goot, Rob
%A Ramponi, Alan
%A Caselli, Tommaso
%A Cafagna, Michele
%A De Mattei, Lorenzo
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F van-der-goot-etal-2020-norm
%X Lexical normalization is the task of translating non-standard social media data to a standard form. Previous work has shown that this is beneficial for many downstream tasks in multiple languages. However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data. In this paper, we discuss the creation of a lexical normalization dataset for Italian. After two rounds of annotation, a Cohen’s kappa score of 78.64 is obtained. During this process, we also analyze the inter-annotator agreement for this task, which is only rarely done on datasets for lexical normalization,and when it is reported, the analysis usually remains shallow. Furthermore, we utilize this dataset to train a lexical normalization model and show that it can be used to improve dependency parsing of social media data. All annotated data and the code to reproduce the results are available at: http://bitbucket.org/robvanderg/normit.
%U https://aclanthology.org/2020.lrec-1.769
%P 6272-6278
Markdown (Informal)
[Norm It! Lexical Normalization for Italian and Its Downstream Effects for Dependency Parsing](https://aclanthology.org/2020.lrec-1.769) (van der Goot et al., LREC 2020)
ACL