@inproceedings{bernier-colborne-etal-2023-dialect,
title = "Dialect and Variant Identification as a Multi-Label Classification Task: A Proposal Based on Near-Duplicate Analysis",
author = "Bernier-colborne, Gabriel and
Goutte, Cyril and
Leger, Serge",
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-1.15",
doi = "10.18653/v1/2023.vardial-1.15",
pages = "142--151",
abstract = "We argue that dialect identification should be treated as a multi-label classification problem rather than the single-class setting prevalent in existing collections and evaluations. In order to avoid extensive human re-labelling of the data, we propose an analysis of ambiguous near-duplicates in an existing collection covering four variants of French.We show how this analysis helps us provide multiple labels for a significant subset of the original data, therefore enriching the annotation with minimal human intervention. The resulting data can then be used to train dialect identifiers in a multi-label setting. Experimental results show that on the enriched dataset, the multi-label classifier produces similar accuracy to the single-label classifier on test cases that are unambiguous (single label), but it increases the macro-averaged F1-score by 0.225 absolute (71{\%} relative gain) on ambiguous texts with multiple labels. On the original data, gains on the ambiguous test cases are smaller but still considerable (+0.077 absolute, 20{\%} relative gain), and accuracy on non-ambiguous test cases is again similar in this case. This supports our thesis that modelling dialect identification as a multi-label problem potentially has a positive impact.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bernier-colborne-etal-2023-dialect">
<titleInfo>
<title>Dialect and Variant Identification as a Multi-Label Classification Task: A Proposal Based on Near-Duplicate Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Bernier-colborne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Goutte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Leger</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 argue that dialect identification should be treated as a multi-label classification problem rather than the single-class setting prevalent in existing collections and evaluations. In order to avoid extensive human re-labelling of the data, we propose an analysis of ambiguous near-duplicates in an existing collection covering four variants of French.We show how this analysis helps us provide multiple labels for a significant subset of the original data, therefore enriching the annotation with minimal human intervention. The resulting data can then be used to train dialect identifiers in a multi-label setting. Experimental results show that on the enriched dataset, the multi-label classifier produces similar accuracy to the single-label classifier on test cases that are unambiguous (single label), but it increases the macro-averaged F1-score by 0.225 absolute (71% relative gain) on ambiguous texts with multiple labels. On the original data, gains on the ambiguous test cases are smaller but still considerable (+0.077 absolute, 20% relative gain), and accuracy on non-ambiguous test cases is again similar in this case. This supports our thesis that modelling dialect identification as a multi-label problem potentially has a positive impact.</abstract>
<identifier type="citekey">bernier-colborne-etal-2023-dialect</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.15</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.15</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>142</start>
<end>151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect and Variant Identification as a Multi-Label Classification Task: A Proposal Based on Near-Duplicate Analysis
%A Bernier-colborne, Gabriel
%A Goutte, Cyril
%A Leger, Serge
%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 bernier-colborne-etal-2023-dialect
%X We argue that dialect identification should be treated as a multi-label classification problem rather than the single-class setting prevalent in existing collections and evaluations. In order to avoid extensive human re-labelling of the data, we propose an analysis of ambiguous near-duplicates in an existing collection covering four variants of French.We show how this analysis helps us provide multiple labels for a significant subset of the original data, therefore enriching the annotation with minimal human intervention. The resulting data can then be used to train dialect identifiers in a multi-label setting. Experimental results show that on the enriched dataset, the multi-label classifier produces similar accuracy to the single-label classifier on test cases that are unambiguous (single label), but it increases the macro-averaged F1-score by 0.225 absolute (71% relative gain) on ambiguous texts with multiple labels. On the original data, gains on the ambiguous test cases are smaller but still considerable (+0.077 absolute, 20% relative gain), and accuracy on non-ambiguous test cases is again similar in this case. This supports our thesis that modelling dialect identification as a multi-label problem potentially has a positive impact.
%R 10.18653/v1/2023.vardial-1.15
%U https://aclanthology.org/2023.vardial-1.15
%U https://doi.org/10.18653/v1/2023.vardial-1.15
%P 142-151
Markdown (Informal)
[Dialect and Variant Identification as a Multi-Label Classification Task: A Proposal Based on Near-Duplicate Analysis](https://aclanthology.org/2023.vardial-1.15) (Bernier-colborne et al., VarDial 2023)
ACL