@inproceedings{benites-etal-2018-twist,
title = "Twist Bytes - {G}erman Dialect Identification with Data Mining Optimization",
author = {Benites, Fernando and
Grubenmann, Ralf and
von D{\"a}niken, Pius and
von Gr{\"u}nigen, Dirk and
Deriu, Jan and
Cieliebak, Mark},
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin and
Ali, Ahmed},
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3925",
pages = "218--227",
abstract = "We describe our approaches used in the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2018. The goal was to identify to which out of four dialects spoken in German speaking part of Switzerland a sentence belonged to. We adopted two different meta classifier approaches and used some data mining insights to improve the preprocessing and the meta classifier parameters. Especially, we focused on using different feature extraction methods and how to combine them, since they influenced very differently the performance of the system. Our system achieved second place out of 8 teams, with a macro averaged F-1 of 64.6{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benites-etal-2018-twist">
<titleInfo>
<title>Twist Bytes - German Dialect Identification with Data Mining Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Benites</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Grubenmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pius</namePart>
<namePart type="family">von Däniken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">von Grünigen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Deriu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Cieliebak</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 Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)</title>
</titleInfo>
<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">Preslav</namePart>
<namePart type="family">Nakov</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>
<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">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe our approaches used in the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2018. The goal was to identify to which out of four dialects spoken in German speaking part of Switzerland a sentence belonged to. We adopted two different meta classifier approaches and used some data mining insights to improve the preprocessing and the meta classifier parameters. Especially, we focused on using different feature extraction methods and how to combine them, since they influenced very differently the performance of the system. Our system achieved second place out of 8 teams, with a macro averaged F-1 of 64.6%.</abstract>
<identifier type="citekey">benites-etal-2018-twist</identifier>
<location>
<url>https://aclanthology.org/W18-3925</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>218</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Twist Bytes - German Dialect Identification with Data Mining Optimization
%A Benites, Fernando
%A Grubenmann, Ralf
%A von Däniken, Pius
%A von Grünigen, Dirk
%A Deriu, Jan
%A Cieliebak, Mark
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%Y Ali, Ahmed
%S Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F benites-etal-2018-twist
%X We describe our approaches used in the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2018. The goal was to identify to which out of four dialects spoken in German speaking part of Switzerland a sentence belonged to. We adopted two different meta classifier approaches and used some data mining insights to improve the preprocessing and the meta classifier parameters. Especially, we focused on using different feature extraction methods and how to combine them, since they influenced very differently the performance of the system. Our system achieved second place out of 8 teams, with a macro averaged F-1 of 64.6%.
%U https://aclanthology.org/W18-3925
%P 218-227
Markdown (Informal)
[Twist Bytes - German Dialect Identification with Data Mining Optimization](https://aclanthology.org/W18-3925) (Benites et al., VarDial 2018)
ACL
- Fernando Benites, Ralf Grubenmann, Pius von Däniken, Dirk von Grünigen, Jan Deriu, and Mark Cieliebak. 2018. Twist Bytes - German Dialect Identification with Data Mining Optimization. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), pages 218–227, Santa Fe, New Mexico, USA. Association for Computational Linguistics.