@inproceedings{hohl-shim-2023-vardial,
title = "{V}ar{D}ial in the Wild: Industrial Applications of {LID} Systems for Closely-Related Language Varieties",
author = "Hohl, Fritz and
Shim, Soh-eun",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, J{\"o}rg and
Zampieri, Marcos},
booktitle = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.vardial-1.21",
doi = "10.18653/v1/2023.vardial-1.21",
pages = "213--221",
abstract = "This report describes first an industrial use case for identifying closely related languages, e.g.dialects, namely the detection of languages of movie subtitle documents. We then presenta 2-stage architecture that is able to detect macrolanguages in the first stage and languagevariants in the second. Using our architecture, we participated in the DSL-TL Shared Task of the VarDial 2023 workshop. We describe the results of our experiments. In the first experiment we report an accuracy of 97.8{\%} on a set of 460 subtitle files. In our second experimentwe used DSL-TL data and achieve a macroaverage F1 of 76{\%} for the binary task, and 54{\%} for the three-way task in the dev set. In the open track, we augment the data with named entities retrieved from Wikidata and achieve minor increases of about 1{\%} for both tracks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hohl-shim-2023-vardial">
<titleInfo>
<title>VarDial in the Wild: Industrial Applications of LID Systems for Closely-Related Language Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fritz</namePart>
<namePart type="family">Hohl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soh-eun</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</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">Preslav</namePart>
<namePart type="family">Nakov</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">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This report describes first an industrial use case for identifying closely related languages, e.g.dialects, namely the detection of languages of movie subtitle documents. We then presenta 2-stage architecture that is able to detect macrolanguages in the first stage and languagevariants in the second. Using our architecture, we participated in the DSL-TL Shared Task of the VarDial 2023 workshop. We describe the results of our experiments. In the first experiment we report an accuracy of 97.8% on a set of 460 subtitle files. In our second experimentwe used DSL-TL data and achieve a macroaverage F1 of 76% for the binary task, and 54% for the three-way task in the dev set. In the open track, we augment the data with named entities retrieved from Wikidata and achieve minor increases of about 1% for both tracks.</abstract>
<identifier type="citekey">hohl-shim-2023-vardial</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.21</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.21</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>213</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VarDial in the Wild: Industrial Applications of LID Systems for Closely-Related Language Varieties
%A Hohl, Fritz
%A Shim, Soh-eun
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F hohl-shim-2023-vardial
%X This report describes first an industrial use case for identifying closely related languages, e.g.dialects, namely the detection of languages of movie subtitle documents. We then presenta 2-stage architecture that is able to detect macrolanguages in the first stage and languagevariants in the second. Using our architecture, we participated in the DSL-TL Shared Task of the VarDial 2023 workshop. We describe the results of our experiments. In the first experiment we report an accuracy of 97.8% on a set of 460 subtitle files. In our second experimentwe used DSL-TL data and achieve a macroaverage F1 of 76% for the binary task, and 54% for the three-way task in the dev set. In the open track, we augment the data with named entities retrieved from Wikidata and achieve minor increases of about 1% for both tracks.
%R 10.18653/v1/2023.vardial-1.21
%U https://aclanthology.org/2023.vardial-1.21
%U https://doi.org/10.18653/v1/2023.vardial-1.21
%P 213-221
Markdown (Informal)
[VarDial in the Wild: Industrial Applications of LID Systems for Closely-Related Language Varieties](https://aclanthology.org/2023.vardial-1.21) (Hohl & Shim, VarDial 2023)
ACL