@inproceedings{ramponi-casula-2023-diatopit,
title = "{D}iatop{I}t: A Corpus of Social Media Posts for the Study of Diatopic Language Variation in {I}taly",
author = "Ramponi, Alan and
Casula, Camilla",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, J{\"o}rg and
Zampieri, Marcos},
booktitle = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.vardial-1.19/",
doi = "10.18653/v1/2023.vardial-1.19",
pages = "187--199",
abstract = "We introduce DiatopIt, the first corpus specifically focused on diatopic language variation in Italy for language varieties other than Standard Italian. DiatopIt comprises over 15K geolocated social media posts from Twitter over a period of two years, including regional Italian usage and content fully written in local language varieties or exhibiting code-switching with Standard Italian. We detail how we tackled key challenges in creating such a resource, including the absence of orthography standards for most local language varieties and the lack of reliable language identification tools. We assess the representativeness of DiatopIt across time and space, and show that the density of non-Standard Italian content across areas correlates with actual language use. We finally conduct computational experiments and find that modeling diatopic variation on highly multilingual areas such as Italy is a complex task even for recent language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramponi-casula-2023-diatopit">
<titleInfo>
<title>DiatopIt: A Corpus of Social Media Posts for the Study of Diatopic Language Variation in Italy</title>
</titleInfo>
<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">Camilla</namePart>
<namePart type="family">Casula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce DiatopIt, the first corpus specifically focused on diatopic language variation in Italy for language varieties other than Standard Italian. DiatopIt comprises over 15K geolocated social media posts from Twitter over a period of two years, including regional Italian usage and content fully written in local language varieties or exhibiting code-switching with Standard Italian. We detail how we tackled key challenges in creating such a resource, including the absence of orthography standards for most local language varieties and the lack of reliable language identification tools. We assess the representativeness of DiatopIt across time and space, and show that the density of non-Standard Italian content across areas correlates with actual language use. We finally conduct computational experiments and find that modeling diatopic variation on highly multilingual areas such as Italy is a complex task even for recent language models.</abstract>
<identifier type="citekey">ramponi-casula-2023-diatopit</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.19/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>187</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiatopIt: A Corpus of Social Media Posts for the Study of Diatopic Language Variation in Italy
%A Ramponi, Alan
%A Casula, Camilla
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F ramponi-casula-2023-diatopit
%X We introduce DiatopIt, the first corpus specifically focused on diatopic language variation in Italy for language varieties other than Standard Italian. DiatopIt comprises over 15K geolocated social media posts from Twitter over a period of two years, including regional Italian usage and content fully written in local language varieties or exhibiting code-switching with Standard Italian. We detail how we tackled key challenges in creating such a resource, including the absence of orthography standards for most local language varieties and the lack of reliable language identification tools. We assess the representativeness of DiatopIt across time and space, and show that the density of non-Standard Italian content across areas correlates with actual language use. We finally conduct computational experiments and find that modeling diatopic variation on highly multilingual areas such as Italy is a complex task even for recent language models.
%R 10.18653/v1/2023.vardial-1.19
%U https://aclanthology.org/2023.vardial-1.19/
%U https://doi.org/10.18653/v1/2023.vardial-1.19
%P 187-199
Markdown (Informal)
[DiatopIt: A Corpus of Social Media Posts for the Study of Diatopic Language Variation in Italy](https://aclanthology.org/2023.vardial-1.19/) (Ramponi & Casula, VarDial 2023)
ACL