@inproceedings{zhang-abdul-mageed-2019-army,
title = "No Army, No Navy: {BERT} Semi-Supervised Learning of {A}rabic Dialects",
author = "Zhang, Chiyu and
Abdul-Mageed, Muhammad",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4637",
doi = "10.18653/v1/W19-4637",
pages = "279--284",
abstract = "We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification. We develop tweet-level identification models based on GRUs and BERT in supervised and semi-supervised set-tings. We then introduce a simple, yet effective, method of porting tweet-level labels at the level of users. Our system ranks top 1 in the competition, with 71.70{\%} macro F1 score and 77.40{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-abdul-mageed-2019-army">
<titleInfo>
<title>No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chiyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification. We develop tweet-level identification models based on GRUs and BERT in supervised and semi-supervised set-tings. We then introduce a simple, yet effective, method of porting tweet-level labels at the level of users. Our system ranks top 1 in the competition, with 71.70% macro F1 score and 77.40% accuracy.</abstract>
<identifier type="citekey">zhang-abdul-mageed-2019-army</identifier>
<identifier type="doi">10.18653/v1/W19-4637</identifier>
<location>
<url>https://aclanthology.org/W19-4637</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>279</start>
<end>284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects
%A Zhang, Chiyu
%A Abdul-Mageed, Muhammad
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F zhang-abdul-mageed-2019-army
%X We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification. We develop tweet-level identification models based on GRUs and BERT in supervised and semi-supervised set-tings. We then introduce a simple, yet effective, method of porting tweet-level labels at the level of users. Our system ranks top 1 in the competition, with 71.70% macro F1 score and 77.40% accuracy.
%R 10.18653/v1/W19-4637
%U https://aclanthology.org/W19-4637
%U https://doi.org/10.18653/v1/W19-4637
%P 279-284
Markdown (Informal)
[No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects](https://aclanthology.org/W19-4637) (Zhang & Abdul-Mageed, WANLP 2019)
ACL