@inproceedings{salameh-etal-2018-fine,
title = "Fine-Grained {A}rabic Dialect Identification",
author = "Salameh, Mohammad and
Bouamor, Houda and
Habash, Nizar",
editor = "Bender, Emily M. and
Derczynski, Leon and
Isabelle, Pierre",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/C18-1113",
pages = "1332--1344",
abstract = "Previous work on the problem of Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic (6-way classification). This paper presents the first results on a fine-grained dialect classification task covering 25 specific cities from across the Arab World, in addition to Standard Arabic {--} a very challenging task. We build several classification systems and explore a large space of features. Our results show that we can identify the exact city of a speaker at an accuracy of 67.9{\%} for sentences with an average length of 7 words (a 9{\%} relative error reduction over the state-of-the-art technique for Arabic dialect identification) and reach more than 90{\%} when we consider 16 words. We also report on additional insights from a data analysis of similarity and difference across Arabic dialects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salameh-etal-2018-fine">
<titleInfo>
<title>Fine-Grained Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Salameh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Bender</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Isabelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work on the problem of Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic (6-way classification). This paper presents the first results on a fine-grained dialect classification task covering 25 specific cities from across the Arab World, in addition to Standard Arabic – a very challenging task. We build several classification systems and explore a large space of features. Our results show that we can identify the exact city of a speaker at an accuracy of 67.9% for sentences with an average length of 7 words (a 9% relative error reduction over the state-of-the-art technique for Arabic dialect identification) and reach more than 90% when we consider 16 words. We also report on additional insights from a data analysis of similarity and difference across Arabic dialects.</abstract>
<identifier type="citekey">salameh-etal-2018-fine</identifier>
<location>
<url>https://aclanthology.org/C18-1113</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>1332</start>
<end>1344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Arabic Dialect Identification
%A Salameh, Mohammad
%A Bouamor, Houda
%A Habash, Nizar
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F salameh-etal-2018-fine
%X Previous work on the problem of Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic (6-way classification). This paper presents the first results on a fine-grained dialect classification task covering 25 specific cities from across the Arab World, in addition to Standard Arabic – a very challenging task. We build several classification systems and explore a large space of features. Our results show that we can identify the exact city of a speaker at an accuracy of 67.9% for sentences with an average length of 7 words (a 9% relative error reduction over the state-of-the-art technique for Arabic dialect identification) and reach more than 90% when we consider 16 words. We also report on additional insights from a data analysis of similarity and difference across Arabic dialects.
%U https://aclanthology.org/C18-1113
%P 1332-1344
Markdown (Informal)
[Fine-Grained Arabic Dialect Identification](https://aclanthology.org/C18-1113) (Salameh et al., COLING 2018)
ACL
- Mohammad Salameh, Houda Bouamor, and Nizar Habash. 2018. Fine-Grained Arabic Dialect Identification. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1332–1344, Santa Fe, New Mexico, USA. Association for Computational Linguistics.