@inproceedings{aloraini-etal-2020-qmul,
title = "The {QMUL}/{HRBDT} contribution to the {NADI} {A}rabic Dialect Identification Shared Task",
author = "Aloraini, Abdulrahman and
Poesio, Massimo and
Alhelbawy, Ayman",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.31",
pages = "295--301",
abstract = "We present the Arabic dialect identification system that we used for the country-level subtask of the NADI challenge. Our model consists of three components: BiLSTM-CNN, character-level TF-IDF, and topic modeling features. We represent each tweet using these features and feed them into a deep neural network. We then add an effective heuristic that improves the overall performance. We achieved an F1-Macro score of 20.77{\%} and an accuracy of 34.32{\%} on the test set. The model was also evaluated on the Arabic Online Commentary dataset, achieving results better than the state-of-the-art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aloraini-etal-2020-qmul">
<titleInfo>
<title>The QMUL/HRBDT contribution to the NADI Arabic Dialect Identification Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Aloraini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayman</namePart>
<namePart type="family">Alhelbawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<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">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</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">Mahmoud</namePart>
<namePart type="family">El-Haj</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">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">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the Arabic dialect identification system that we used for the country-level subtask of the NADI challenge. Our model consists of three components: BiLSTM-CNN, character-level TF-IDF, and topic modeling features. We represent each tweet using these features and feed them into a deep neural network. We then add an effective heuristic that improves the overall performance. We achieved an F1-Macro score of 20.77% and an accuracy of 34.32% on the test set. The model was also evaluated on the Arabic Online Commentary dataset, achieving results better than the state-of-the-art.</abstract>
<identifier type="citekey">aloraini-etal-2020-qmul</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.31</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>295</start>
<end>301</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The QMUL/HRBDT contribution to the NADI Arabic Dialect Identification Shared Task
%A Aloraini, Abdulrahman
%A Poesio, Massimo
%A Alhelbawy, Ayman
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F aloraini-etal-2020-qmul
%X We present the Arabic dialect identification system that we used for the country-level subtask of the NADI challenge. Our model consists of three components: BiLSTM-CNN, character-level TF-IDF, and topic modeling features. We represent each tweet using these features and feed them into a deep neural network. We then add an effective heuristic that improves the overall performance. We achieved an F1-Macro score of 20.77% and an accuracy of 34.32% on the test set. The model was also evaluated on the Arabic Online Commentary dataset, achieving results better than the state-of-the-art.
%U https://aclanthology.org/2020.wanlp-1.31
%P 295-301
Markdown (Informal)
[The QMUL/HRBDT contribution to the NADI Arabic Dialect Identification Shared Task](https://aclanthology.org/2020.wanlp-1.31) (Aloraini et al., WANLP 2020)
ACL