@inproceedings{eltanbouly-etal-2019-simple,
title = {Simple But Not Na{\"\i}ve: Fine-Grained {A}rabic Dialect Identification Using Only N-Grams},
author = "Eltanbouly, Sohaila and
Bashendy, May and
Elsayed, Tamer",
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/W19-4624",
doi = "10.18653/v1/W19-4624",
pages = "214--218",
abstract = "This paper presents the participation of Qatar University team in MADAR shared task, which addresses the problem of sentence-level fine-grained Arabic Dialect Identification over 25 different Arabic dialects in addition to the Modern Standard Arabic. Arabic Dialect Identification is not a trivial task since different dialects share some features, e.g., utilizing the same character set and some vocabularies. We opted to adopt a very simple approach in terms of extracted features and classification models; we only utilize word and character n-grams as features, and Na ̈{\i}ve Bayes models as classifiers. Surprisingly, the simple approach achieved non-na ̈{\i}ve performance. The official results, reported on a held-out testing set, show that the dialect of a given sentence can be identified at an accuracy of 64.58{\%} by our best submitted run.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eltanbouly-etal-2019-simple">
<titleInfo>
<title>Simple But Not Naïve: Fine-Grained Arabic Dialect Identification Using Only N-Grams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohaila</namePart>
<namePart type="family">Eltanbouly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">May</namePart>
<namePart type="family">Bashendy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</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>This paper presents the participation of Qatar University team in MADAR shared task, which addresses the problem of sentence-level fine-grained Arabic Dialect Identification over 25 different Arabic dialects in addition to the Modern Standard Arabic. Arabic Dialect Identification is not a trivial task since different dialects share some features, e.g., utilizing the same character set and some vocabularies. We opted to adopt a very simple approach in terms of extracted features and classification models; we only utilize word and character n-grams as features, and Na ̈ıve Bayes models as classifiers. Surprisingly, the simple approach achieved non-na ̈ıve performance. The official results, reported on a held-out testing set, show that the dialect of a given sentence can be identified at an accuracy of 64.58% by our best submitted run.</abstract>
<identifier type="citekey">eltanbouly-etal-2019-simple</identifier>
<identifier type="doi">10.18653/v1/W19-4624</identifier>
<location>
<url>https://aclanthology.org/W19-4624</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>214</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple But Not Naïve: Fine-Grained Arabic Dialect Identification Using Only N-Grams
%A Eltanbouly, Sohaila
%A Bashendy, May
%A Elsayed, Tamer
%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 eltanbouly-etal-2019-simple
%X This paper presents the participation of Qatar University team in MADAR shared task, which addresses the problem of sentence-level fine-grained Arabic Dialect Identification over 25 different Arabic dialects in addition to the Modern Standard Arabic. Arabic Dialect Identification is not a trivial task since different dialects share some features, e.g., utilizing the same character set and some vocabularies. We opted to adopt a very simple approach in terms of extracted features and classification models; we only utilize word and character n-grams as features, and Na ̈ıve Bayes models as classifiers. Surprisingly, the simple approach achieved non-na ̈ıve performance. The official results, reported on a held-out testing set, show that the dialect of a given sentence can be identified at an accuracy of 64.58% by our best submitted run.
%R 10.18653/v1/W19-4624
%U https://aclanthology.org/W19-4624
%U https://doi.org/10.18653/v1/W19-4624
%P 214-218
Markdown (Informal)
[Simple But Not Naïve: Fine-Grained Arabic Dialect Identification Using Only N-Grams](https://aclanthology.org/W19-4624) (Eltanbouly et al., WANLP 2019)
ACL