@inproceedings{ionescu-butnaru-2017-learning,
title = "Learning to Identify {A}rabic and {G}erman Dialects using Multiple Kernels",
author = "Ionescu, Radu Tudor and
Butnaru, Andrei",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shevin and
Ali, Ahmed},
booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1225",
doi = "10.18653/v1/W17-1225",
pages = "200--209",
abstract = "We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge. The proposed approach combines several kernels using multiple kernel learning. While most of our kernels are based on character p-grams (also known as n-grams) extracted from speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided only for the Arabic data. In the learning stage, we independently employ Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR). Our approach is shallow and simple, but the empirical results obtained in the shared tasks prove that it achieves very good results. Indeed, we ranked on the first place in the ADI Shared Task with a weighted F1 score of 76.32{\%} (4.62{\%} above the second place) and on the fifth place in the GDI Shared Task with a weighted F1 score of 63.67{\%} (2.57{\%} below the first place).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ionescu-butnaru-2017-learning">
<titleInfo>
<title>Learning to Identify Arabic and German Dialects using Multiple 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">Andrei</namePart>
<namePart type="family">Butnaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)</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">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">Shevin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge. The proposed approach combines several kernels using multiple kernel learning. While most of our kernels are based on character p-grams (also known as n-grams) extracted from speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided only for the Arabic data. In the learning stage, we independently employ Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR). Our approach is shallow and simple, but the empirical results obtained in the shared tasks prove that it achieves very good results. Indeed, we ranked on the first place in the ADI Shared Task with a weighted F1 score of 76.32% (4.62% above the second place) and on the fifth place in the GDI Shared Task with a weighted F1 score of 63.67% (2.57% below the first place).</abstract>
<identifier type="citekey">ionescu-butnaru-2017-learning</identifier>
<identifier type="doi">10.18653/v1/W17-1225</identifier>
<location>
<url>https://aclanthology.org/W17-1225</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>200</start>
<end>209</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Identify Arabic and German Dialects using Multiple Kernels
%A Ionescu, Radu Tudor
%A Butnaru, Andrei
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shevin
%Y Ali, Ahmed
%S Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F ionescu-butnaru-2017-learning
%X We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge. The proposed approach combines several kernels using multiple kernel learning. While most of our kernels are based on character p-grams (also known as n-grams) extracted from speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided only for the Arabic data. In the learning stage, we independently employ Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR). Our approach is shallow and simple, but the empirical results obtained in the shared tasks prove that it achieves very good results. Indeed, we ranked on the first place in the ADI Shared Task with a weighted F1 score of 76.32% (4.62% above the second place) and on the fifth place in the GDI Shared Task with a weighted F1 score of 63.67% (2.57% below the first place).
%R 10.18653/v1/W17-1225
%U https://aclanthology.org/W17-1225
%U https://doi.org/10.18653/v1/W17-1225
%P 200-209
Markdown (Informal)
[Learning to Identify Arabic and German Dialects using Multiple Kernels](https://aclanthology.org/W17-1225) (Ionescu & Butnaru, VarDial 2017)
ACL