@inproceedings{alshutayri-etal-2016-arabic,
title = "{A}rabic Language {WEKA}-Based Dialect Classifier for {A}rabic Automatic Speech Recognition Transcripts",
author = "Alshutayri, Areej and
Atwell, Eric and
Alosaimy, Abdulrahman and
Dickins, James and
Ingleby, Michael and
Watson, Janet",
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/W16-4826",
pages = "204--211",
abstract = "This paper describes an Arabic dialect identification system which we developed for the Discriminating Similar Languages (DSL) 2016 shared task. We classified Arabic dialects by using Waikato Environment for Knowledge Analysis (WEKA) data analytic tool which contains many alternative filters and classifiers for machine learning. We experimented with several classifiers and the best accuracy was achieved using the Sequential Minimal Optimization (SMO) algorithm for training and testing process set to three different feature-sets for each testing process. Our approach achieved an accuracy equal to 42.85{\%} which is considerably worse in comparison to the evaluation scores on the training set of 80-90{\%} and with training set {``}60:40{''} percentage split which achieved accuracy around 50{\%}. We observed that Buckwalter transcripts from the Saarland Automatic Speech Recognition (ASR) system are given without short vowels, though the Buckwalter system has notation for these. We elaborate such observations, describe our methods and analyse the training dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshutayri-etal-2016-arabic">
<titleInfo>
<title>Arabic Language WEKA-Based Dialect Classifier for Arabic Automatic Speech Recognition Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Areej</namePart>
<namePart type="family">Alshutayri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Alosaimy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Dickins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ingleby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janet</namePart>
<namePart type="family">Watson</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>This paper describes an Arabic dialect identification system which we developed for the Discriminating Similar Languages (DSL) 2016 shared task. We classified Arabic dialects by using Waikato Environment for Knowledge Analysis (WEKA) data analytic tool which contains many alternative filters and classifiers for machine learning. We experimented with several classifiers and the best accuracy was achieved using the Sequential Minimal Optimization (SMO) algorithm for training and testing process set to three different feature-sets for each testing process. Our approach achieved an accuracy equal to 42.85% which is considerably worse in comparison to the evaluation scores on the training set of 80-90% and with training set “60:40” percentage split which achieved accuracy around 50%. We observed that Buckwalter transcripts from the Saarland Automatic Speech Recognition (ASR) system are given without short vowels, though the Buckwalter system has notation for these. We elaborate such observations, describe our methods and analyse the training dataset.</abstract>
<identifier type="citekey">alshutayri-etal-2016-arabic</identifier>
<location>
<url>https://aclanthology.org/W16-4826</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>204</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Language WEKA-Based Dialect Classifier for Arabic Automatic Speech Recognition Transcripts
%A Alshutayri, Areej
%A Atwell, Eric
%A Alosaimy, Abdulrahman
%A Dickins, James
%A Ingleby, Michael
%A Watson, Janet
%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 alshutayri-etal-2016-arabic
%X This paper describes an Arabic dialect identification system which we developed for the Discriminating Similar Languages (DSL) 2016 shared task. We classified Arabic dialects by using Waikato Environment for Knowledge Analysis (WEKA) data analytic tool which contains many alternative filters and classifiers for machine learning. We experimented with several classifiers and the best accuracy was achieved using the Sequential Minimal Optimization (SMO) algorithm for training and testing process set to three different feature-sets for each testing process. Our approach achieved an accuracy equal to 42.85% which is considerably worse in comparison to the evaluation scores on the training set of 80-90% and with training set “60:40” percentage split which achieved accuracy around 50%. We observed that Buckwalter transcripts from the Saarland Automatic Speech Recognition (ASR) system are given without short vowels, though the Buckwalter system has notation for these. We elaborate such observations, describe our methods and analyse the training dataset.
%U https://aclanthology.org/W16-4826
%P 204-211
Markdown (Informal)
[Arabic Language WEKA-Based Dialect Classifier for Arabic Automatic Speech Recognition Transcripts](https://aclanthology.org/W16-4826) (Alshutayri et al., VarDial 2016)
ACL