@inproceedings{abu-kwaik-saad-2019-arbdialectid,
title = "{A}rb{D}ialect{ID} at {MADAR} Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained {A}rabic Dialect Identification",
author = "Abu Kwaik, Kathrein and
Saad, Motaz",
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/W19-4632",
doi = "10.18653/v1/W19-4632",
pages = "254--258",
abstract = "In this paper, we present a Dialect Identification system (ArbDialectID) that competed at Task 1 of the MADAR shared task, MADARTravel Domain Dialect Identification. We build a course and a fine-grained identification model to predict the label (corresponding to a dialect of Arabic) of a given text. We build two language models by extracting features at two levels (words and characters). We firstly build a coarse identification model to classify each sentence into one out of six dialects, then use this label as a feature for the fine-grained model that classifies the sentence among 26 dialects from different Arab cities, after that we apply ensemble voting classifier on both sub-systems. Our system ranked 1st that achieving an f-score of 67.32{\%}. Both the models and our feature engineering tools are made available to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abu-kwaik-saad-2019-arbdialectid">
<titleInfo>
<title>ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathrein</namePart>
<namePart type="family">Abu Kwaik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Motaz</namePart>
<namePart type="family">Saad</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>In this paper, we present a Dialect Identification system (ArbDialectID) that competed at Task 1 of the MADAR shared task, MADARTravel Domain Dialect Identification. We build a course and a fine-grained identification model to predict the label (corresponding to a dialect of Arabic) of a given text. We build two language models by extracting features at two levels (words and characters). We firstly build a coarse identification model to classify each sentence into one out of six dialects, then use this label as a feature for the fine-grained model that classifies the sentence among 26 dialects from different Arab cities, after that we apply ensemble voting classifier on both sub-systems. Our system ranked 1st that achieving an f-score of 67.32%. Both the models and our feature engineering tools are made available to the research community.</abstract>
<identifier type="citekey">abu-kwaik-saad-2019-arbdialectid</identifier>
<identifier type="doi">10.18653/v1/W19-4632</identifier>
<location>
<url>https://aclanthology.org/W19-4632</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>254</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification
%A Abu Kwaik, Kathrein
%A Saad, Motaz
%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 abu-kwaik-saad-2019-arbdialectid
%X In this paper, we present a Dialect Identification system (ArbDialectID) that competed at Task 1 of the MADAR shared task, MADARTravel Domain Dialect Identification. We build a course and a fine-grained identification model to predict the label (corresponding to a dialect of Arabic) of a given text. We build two language models by extracting features at two levels (words and characters). We firstly build a coarse identification model to classify each sentence into one out of six dialects, then use this label as a feature for the fine-grained model that classifies the sentence among 26 dialects from different Arab cities, after that we apply ensemble voting classifier on both sub-systems. Our system ranked 1st that achieving an f-score of 67.32%. Both the models and our feature engineering tools are made available to the research community.
%R 10.18653/v1/W19-4632
%U https://aclanthology.org/W19-4632
%U https://doi.org/10.18653/v1/W19-4632
%P 254-258
Markdown (Informal)
[ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification](https://aclanthology.org/W19-4632) (Abu Kwaik & Saad, WANLP 2019)
ACL