@inproceedings{zaharia-etal-2021-dialect,
title = "Dialect Identification through Adversarial Learning and Knowledge Distillation on {R}omanian {BERT}",
author = "Zaharia, George-Eduard and
Avram, Andrei-Marius and
Cercel, Dumitru-Clementin and
Rebedea, Traian",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Scherrer, Yves and
Jauhiainen, Tommi},
booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.vardial-1.13/",
pages = "113--119",
abstract = "Dialect identification is a task with applicability in a vast array of domains, ranging from automatic speech recognition to opinion mining. This work presents our architectures used for the VarDial 2021 Romanian Dialect Identification subtask. We introduced a series of solutions based on Romanian or multilingual Transformers, as well as adversarial training techniques. At the same time, we experimented with a knowledge distillation tool in order to check whether a smaller model can maintain the performance of our best approach. Our best solution managed to obtain a weighted F1-score of 0.7324, allowing us to obtain the 2nd place on the leaderboard."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaharia-etal-2021-dialect">
<titleInfo>
<title>Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">George-Eduard</namePart>
<namePart type="family">Zaharia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei-Marius</namePart>
<namePart type="family">Avram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<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">Nikola</namePart>
<namePart type="family">Ljubešić</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">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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialect identification is a task with applicability in a vast array of domains, ranging from automatic speech recognition to opinion mining. This work presents our architectures used for the VarDial 2021 Romanian Dialect Identification subtask. We introduced a series of solutions based on Romanian or multilingual Transformers, as well as adversarial training techniques. At the same time, we experimented with a knowledge distillation tool in order to check whether a smaller model can maintain the performance of our best approach. Our best solution managed to obtain a weighted F1-score of 0.7324, allowing us to obtain the 2nd place on the leaderboard.</abstract>
<identifier type="citekey">zaharia-etal-2021-dialect</identifier>
<location>
<url>https://aclanthology.org/2021.vardial-1.13/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>113</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT
%A Zaharia, George-Eduard
%A Avram, Andrei-Marius
%A Cercel, Dumitru-Clementin
%A Rebedea, Traian
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%S Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F zaharia-etal-2021-dialect
%X Dialect identification is a task with applicability in a vast array of domains, ranging from automatic speech recognition to opinion mining. This work presents our architectures used for the VarDial 2021 Romanian Dialect Identification subtask. We introduced a series of solutions based on Romanian or multilingual Transformers, as well as adversarial training techniques. At the same time, we experimented with a knowledge distillation tool in order to check whether a smaller model can maintain the performance of our best approach. Our best solution managed to obtain a weighted F1-score of 0.7324, allowing us to obtain the 2nd place on the leaderboard.
%U https://aclanthology.org/2021.vardial-1.13/
%P 113-119
Markdown (Informal)
[Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT](https://aclanthology.org/2021.vardial-1.13/) (Zaharia et al., VarDial 2021)
ACL