@inproceedings{ionescu-popescu-2016-unibuckernel,
title = "{U}nibuc{K}ernel: An Approach for {A}rabic Dialect Identification Based on Multiple String Kernels",
author = "Ionescu, Radu Tudor and
Popescu, Marius",
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/W16-4818",
pages = "135--144",
abstract = "The most common approach in text mining classification tasks is to rely on features like words, part-of-speech tags, stems, or some other high-level linguistic features. Unlike the common approach, we present a method that uses only character p-grams (also known as n-grams) as features for the Arabic Dialect Identification (ADI) Closed Shared Task of the DSL 2016 Challenge. The proposed approach combines several string kernels using multiple kernel learning. In the learning stage, we try both Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR), and we choose KDA as it gives better results in a 10-fold cross-validation carried out on the training set. Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results. Indeed, we ranked on the second place with an accuracy of 50.91{\%} and a weighted F1 score of 51.31{\%}. We also present improved results in this paper, which we obtained after the competition ended. Simply by adding more regularization into our model to make it more suitable for test data that comes from a different distribution than training data, we obtain an accuracy of 51.82{\%} and a weighted F1 score of 52.18{\%}. Furthermore, the proposed approach has an important advantage in that it is language independent and linguistic theory neutral, as it does not require any NLP tools.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ionescu-popescu-2016-unibuckernel">
<titleInfo>
<title>UnibucKernel: An Approach for Arabic Dialect Identification Based on Multiple String Kernels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="given">Tudor</namePart>
<namePart type="family">Ionescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Popescu</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>The most common approach in text mining classification tasks is to rely on features like words, part-of-speech tags, stems, or some other high-level linguistic features. Unlike the common approach, we present a method that uses only character p-grams (also known as n-grams) as features for the Arabic Dialect Identification (ADI) Closed Shared Task of the DSL 2016 Challenge. The proposed approach combines several string kernels using multiple kernel learning. In the learning stage, we try both Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR), and we choose KDA as it gives better results in a 10-fold cross-validation carried out on the training set. Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results. Indeed, we ranked on the second place with an accuracy of 50.91% and a weighted F1 score of 51.31%. We also present improved results in this paper, which we obtained after the competition ended. Simply by adding more regularization into our model to make it more suitable for test data that comes from a different distribution than training data, we obtain an accuracy of 51.82% and a weighted F1 score of 52.18%. Furthermore, the proposed approach has an important advantage in that it is language independent and linguistic theory neutral, as it does not require any NLP tools.</abstract>
<identifier type="citekey">ionescu-popescu-2016-unibuckernel</identifier>
<location>
<url>https://aclanthology.org/W16-4818</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>135</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnibucKernel: An Approach for Arabic Dialect Identification Based on Multiple String Kernels
%A Ionescu, Radu Tudor
%A Popescu, Marius
%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 ionescu-popescu-2016-unibuckernel
%X The most common approach in text mining classification tasks is to rely on features like words, part-of-speech tags, stems, or some other high-level linguistic features. Unlike the common approach, we present a method that uses only character p-grams (also known as n-grams) as features for the Arabic Dialect Identification (ADI) Closed Shared Task of the DSL 2016 Challenge. The proposed approach combines several string kernels using multiple kernel learning. In the learning stage, we try both Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR), and we choose KDA as it gives better results in a 10-fold cross-validation carried out on the training set. Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results. Indeed, we ranked on the second place with an accuracy of 50.91% and a weighted F1 score of 51.31%. We also present improved results in this paper, which we obtained after the competition ended. Simply by adding more regularization into our model to make it more suitable for test data that comes from a different distribution than training data, we obtain an accuracy of 51.82% and a weighted F1 score of 52.18%. Furthermore, the proposed approach has an important advantage in that it is language independent and linguistic theory neutral, as it does not require any NLP tools.
%U https://aclanthology.org/W16-4818
%P 135-144
Markdown (Informal)
[UnibucKernel: An Approach for Arabic Dialect Identification Based on Multiple String Kernels](https://aclanthology.org/W16-4818) (Ionescu & Popescu, VarDial 2016)
ACL