@inproceedings{gaman-2023-using,
title = "Using Ensemble Learning in Language Variety Identification",
author = "Gaman, Mihaela",
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-1.23",
doi = "10.18653/v1/2023.vardial-1.23",
pages = "230--240",
abstract = "The present work describes the solutions pro- posed by the UnibucNLP team to address the closed format of the DSL-TL task featured in the tenth VarDial Evaluation Campaign. The DSL-TL organizers provided approximately 11 thousand sentences written in three different languages and manually tagged with one of 9 classes. Out of these, 3 tags are considered common label and the remaining 6 tags are variety-specific. The DSL-TL task features 2 subtasks: Track 1 - a three-way and Track 2 - a two-way classification per language. In Track 2 only the variety-specific labels are used for scoring, whereas in Track 1 the common label is considered as well. Our team participated in both tracks, with three ensemble-based sub- missions for each. The meta-learner used for Track 1 is XGBoost and for Track 2, Logis- tic Regression. With each submission, we are gradually increasing the complexity of the en- semble, starting with two shallow, string-kernel based methods. To the first ensemble, we add a convolutional neural network for our second submission. The third ensemble submitted adds a fine-tuned BERT model to the second one. In Track 1, ensemble three is our highest ranked, with an F1 − score of 53.18{\%}; 5.36{\%} less than the leader. Surprisingly, in Track 2 the en- semble of shallow methods surpasses the other two, more complex ensembles, achieving an F 1 − score of 69.35{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaman-2023-using">
<titleInfo>
<title>Using Ensemble Learning in Language Variety Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihaela</namePart>
<namePart type="family">Gaman</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>The present work describes the solutions pro- posed by the UnibucNLP team to address the closed format of the DSL-TL task featured in the tenth VarDial Evaluation Campaign. The DSL-TL organizers provided approximately 11 thousand sentences written in three different languages and manually tagged with one of 9 classes. Out of these, 3 tags are considered common label and the remaining 6 tags are variety-specific. The DSL-TL task features 2 subtasks: Track 1 - a three-way and Track 2 - a two-way classification per language. In Track 2 only the variety-specific labels are used for scoring, whereas in Track 1 the common label is considered as well. Our team participated in both tracks, with three ensemble-based sub- missions for each. The meta-learner used for Track 1 is XGBoost and for Track 2, Logis- tic Regression. With each submission, we are gradually increasing the complexity of the en- semble, starting with two shallow, string-kernel based methods. To the first ensemble, we add a convolutional neural network for our second submission. The third ensemble submitted adds a fine-tuned BERT model to the second one. In Track 1, ensemble three is our highest ranked, with an F1 − score of 53.18%; 5.36% less than the leader. Surprisingly, in Track 2 the en- semble of shallow methods surpasses the other two, more complex ensembles, achieving an F 1 − score of 69.35%.</abstract>
<identifier type="citekey">gaman-2023-using</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.23</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.23</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>230</start>
<end>240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Ensemble Learning in Language Variety Identification
%A Gaman, Mihaela
%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 gaman-2023-using
%X The present work describes the solutions pro- posed by the UnibucNLP team to address the closed format of the DSL-TL task featured in the tenth VarDial Evaluation Campaign. The DSL-TL organizers provided approximately 11 thousand sentences written in three different languages and manually tagged with one of 9 classes. Out of these, 3 tags are considered common label and the remaining 6 tags are variety-specific. The DSL-TL task features 2 subtasks: Track 1 - a three-way and Track 2 - a two-way classification per language. In Track 2 only the variety-specific labels are used for scoring, whereas in Track 1 the common label is considered as well. Our team participated in both tracks, with three ensemble-based sub- missions for each. The meta-learner used for Track 1 is XGBoost and for Track 2, Logis- tic Regression. With each submission, we are gradually increasing the complexity of the en- semble, starting with two shallow, string-kernel based methods. To the first ensemble, we add a convolutional neural network for our second submission. The third ensemble submitted adds a fine-tuned BERT model to the second one. In Track 1, ensemble three is our highest ranked, with an F1 − score of 53.18%; 5.36% less than the leader. Surprisingly, in Track 2 the en- semble of shallow methods surpasses the other two, more complex ensembles, achieving an F 1 − score of 69.35%.
%R 10.18653/v1/2023.vardial-1.23
%U https://aclanthology.org/2023.vardial-1.23
%U https://doi.org/10.18653/v1/2023.vardial-1.23
%P 230-240
Markdown (Informal)
[Using Ensemble Learning in Language Variety Identification](https://aclanthology.org/2023.vardial-1.23) (Gaman, VarDial 2023)
ACL