@inproceedings{malmasi-zampieri-2016-arabic,
title = "{A}rabic Dialect Identification in Speech Transcripts",
author = "Malmasi, Shervin and
Zampieri, Marcos",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Tan, Liling and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin},
booktitle = "Proceedings of the Third Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial3)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4814",
pages = "106--113",
abstract = "In this paper we describe a system developed to identify a set of four regional Arabic dialects (Egyptian, Gulf, Levantine, North African) and Modern Standard Arabic (MSA) in a transcribed speech corpus. We competed under the team name MAZA in the Arabic Dialect Identification sub-task of the 2016 Discriminating between Similar Languages (DSL) shared task. Our system achieved an F1-score of 0.51 in the closed training track, ranking first among the 18 teams that participated in the sub-task. Our system utilizes a classifier ensemble with a set of linear models as base classifiers. We experimented with three different ensemble fusion strategies, with the mean probability approach providing the best performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malmasi-zampieri-2016-arabic">
<titleInfo>
<title>Arabic Dialect Identification in Speech Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe a system developed to identify a set of four regional Arabic dialects (Egyptian, Gulf, Levantine, North African) and Modern Standard Arabic (MSA) in a transcribed speech corpus. We competed under the team name MAZA in the Arabic Dialect Identification sub-task of the 2016 Discriminating between Similar Languages (DSL) shared task. Our system achieved an F1-score of 0.51 in the closed training track, ranking first among the 18 teams that participated in the sub-task. Our system utilizes a classifier ensemble with a set of linear models as base classifiers. We experimented with three different ensemble fusion strategies, with the mean probability approach providing the best performance.</abstract>
<identifier type="citekey">malmasi-zampieri-2016-arabic</identifier>
<location>
<url>https://aclanthology.org/W16-4814</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>106</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Dialect Identification in Speech Transcripts
%A Malmasi, Shervin
%A Zampieri, Marcos
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Tan, Liling
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%S Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F malmasi-zampieri-2016-arabic
%X In this paper we describe a system developed to identify a set of four regional Arabic dialects (Egyptian, Gulf, Levantine, North African) and Modern Standard Arabic (MSA) in a transcribed speech corpus. We competed under the team name MAZA in the Arabic Dialect Identification sub-task of the 2016 Discriminating between Similar Languages (DSL) shared task. Our system achieved an F1-score of 0.51 in the closed training track, ranking first among the 18 teams that participated in the sub-task. Our system utilizes a classifier ensemble with a set of linear models as base classifiers. We experimented with three different ensemble fusion strategies, with the mean probability approach providing the best performance.
%U https://aclanthology.org/W16-4814
%P 106-113
Markdown (Informal)
[Arabic Dialect Identification in Speech Transcripts](https://aclanthology.org/W16-4814) (Malmasi & Zampieri, VarDial 2016)
ACL
- Shervin Malmasi and Marcos Zampieri. 2016. Arabic Dialect Identification in Speech Transcripts. In Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3), pages 106–113, Osaka, Japan. The COLING 2016 Organizing Committee.