@inproceedings{espana-bonet-etal-2024-elote,
title = "When Elote, Choclo and Mazorca are not the Same. Isomorphism-Based Perspective to the {S}panish Varieties Divergences",
author = "Espa{\~n}a-Bonet, Cristina and
Bhatt, Ankur and
Dutta Chowdhury, Koel and
Barr{\'o}n-Cede{\~n}o, Alberto",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Zampieri, Marcos and
Nakov, Preslav and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.vardial-1.5",
doi = "10.18653/v1/2024.vardial-1.5",
pages = "56--77",
abstract = "Spanish is an official language in 20 countries; in 19 of them, it arrived by means of overseas colonisation. Its close contact with several coexistent languages and the rich regional and cultural diversity has produced varieties which divert from each other. We study these divergences in a data-based approach and according to their qualitative and quantitative effects in word embeddings. We generate embeddings for Spanish in 24 countries and examine the topology of the spaces. Due to the similarities between varieties {---}in contrast to what happens to different languages in bilingual topological studies{---} we first scrutinise the behaviour of three isomorphism measures in (quasi-)isomorphic settings: relational similarity, Eigenvalue similarity and Gromov-Hausdorff distance. We then use the most trustworthy measure to quantify the divergences among varieties. Finally, we use the departures from isomorphism to build relational trees for the Spanish varieties by hierarchical clustering.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="espana-bonet-etal-2024-elote">
<titleInfo>
<title>When Elote, Choclo and Mazorca are not the Same. Isomorphism-Based Perspective to the Spanish Varieties Divergences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España-Bonet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Bhatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koel</namePart>
<namePart type="family">Dutta Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)</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">Marcos</namePart>
<namePart type="family">Zampieri</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spanish is an official language in 20 countries; in 19 of them, it arrived by means of overseas colonisation. Its close contact with several coexistent languages and the rich regional and cultural diversity has produced varieties which divert from each other. We study these divergences in a data-based approach and according to their qualitative and quantitative effects in word embeddings. We generate embeddings for Spanish in 24 countries and examine the topology of the spaces. Due to the similarities between varieties —in contrast to what happens to different languages in bilingual topological studies— we first scrutinise the behaviour of three isomorphism measures in (quasi-)isomorphic settings: relational similarity, Eigenvalue similarity and Gromov-Hausdorff distance. We then use the most trustworthy measure to quantify the divergences among varieties. Finally, we use the departures from isomorphism to build relational trees for the Spanish varieties by hierarchical clustering.</abstract>
<identifier type="citekey">espana-bonet-etal-2024-elote</identifier>
<identifier type="doi">10.18653/v1/2024.vardial-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.vardial-1.5</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>56</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Elote, Choclo and Mazorca are not the Same. Isomorphism-Based Perspective to the Spanish Varieties Divergences
%A España-Bonet, Cristina
%A Bhatt, Ankur
%A Dutta Chowdhury, Koel
%A Barrón-Cedeño, Alberto
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%S Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F espana-bonet-etal-2024-elote
%X Spanish is an official language in 20 countries; in 19 of them, it arrived by means of overseas colonisation. Its close contact with several coexistent languages and the rich regional and cultural diversity has produced varieties which divert from each other. We study these divergences in a data-based approach and according to their qualitative and quantitative effects in word embeddings. We generate embeddings for Spanish in 24 countries and examine the topology of the spaces. Due to the similarities between varieties —in contrast to what happens to different languages in bilingual topological studies— we first scrutinise the behaviour of three isomorphism measures in (quasi-)isomorphic settings: relational similarity, Eigenvalue similarity and Gromov-Hausdorff distance. We then use the most trustworthy measure to quantify the divergences among varieties. Finally, we use the departures from isomorphism to build relational trees for the Spanish varieties by hierarchical clustering.
%R 10.18653/v1/2024.vardial-1.5
%U https://aclanthology.org/2024.vardial-1.5
%U https://doi.org/10.18653/v1/2024.vardial-1.5
%P 56-77
Markdown (Informal)
[When Elote, Choclo and Mazorca are not the Same. Isomorphism-Based Perspective to the Spanish Varieties Divergences](https://aclanthology.org/2024.vardial-1.5) (España-Bonet et al., VarDial-WS 2024)
ACL