@inproceedings{rupnik-etal-2023-benchic,
title = "{BENCH}i{\'c}-lang: A Benchmark for Discriminating between {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
author = "Rupnik, Peter and
Kuzman, Taja and
Ljube{\v{s}}i{\'c}, Nikola",
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-1.11",
doi = "10.18653/v1/2023.vardial-1.11",
pages = "113--120",
abstract = "Automatic discrimination between Bosnian, Croatian, Montenegrin and Serbian is a hard task due to the mutual intelligibility of these South-Slavic languages. In this paper, we introduce the BENCHi{\'c}-lang benchmark for discriminating between these four languages. The benchmark consists of two datasets from different domains - a Twitter and a news dataset - selected with the aim of fostering cross-dataset evaluation of different modelling approaches. We experiment with the baseline SVM models, based on character n-grams, which perform nicely in-dataset, but do not generalize well in cross-dataset experiments. Thus, we introduce another approach, exploiting only web-crawled data and the weak supervision signal coming from the respective country/language top-level domains. The resulting simple Naive Bayes model, based on less than a thousand word features extracted from web data, outperforms the baseline models in the cross-dataset scenario and achieves good levels of generalization across datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rupnik-etal-2023-benchic">
<titleInfo>
<title>BENCHić-lang: A Benchmark for Discriminating between Bosnian, Croatian, Montenegrin and Serbian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Rupnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taja</namePart>
<namePart type="family">Kuzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</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>Automatic discrimination between Bosnian, Croatian, Montenegrin and Serbian is a hard task due to the mutual intelligibility of these South-Slavic languages. In this paper, we introduce the BENCHić-lang benchmark for discriminating between these four languages. The benchmark consists of two datasets from different domains - a Twitter and a news dataset - selected with the aim of fostering cross-dataset evaluation of different modelling approaches. We experiment with the baseline SVM models, based on character n-grams, which perform nicely in-dataset, but do not generalize well in cross-dataset experiments. Thus, we introduce another approach, exploiting only web-crawled data and the weak supervision signal coming from the respective country/language top-level domains. The resulting simple Naive Bayes model, based on less than a thousand word features extracted from web data, outperforms the baseline models in the cross-dataset scenario and achieves good levels of generalization across datasets.</abstract>
<identifier type="citekey">rupnik-etal-2023-benchic</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.11</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.11</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>113</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BENCHić-lang: A Benchmark for Discriminating between Bosnian, Croatian, Montenegrin and Serbian
%A Rupnik, Peter
%A Kuzman, Taja
%A Ljubešić, Nikola
%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 rupnik-etal-2023-benchic
%X Automatic discrimination between Bosnian, Croatian, Montenegrin and Serbian is a hard task due to the mutual intelligibility of these South-Slavic languages. In this paper, we introduce the BENCHić-lang benchmark for discriminating between these four languages. The benchmark consists of two datasets from different domains - a Twitter and a news dataset - selected with the aim of fostering cross-dataset evaluation of different modelling approaches. We experiment with the baseline SVM models, based on character n-grams, which perform nicely in-dataset, but do not generalize well in cross-dataset experiments. Thus, we introduce another approach, exploiting only web-crawled data and the weak supervision signal coming from the respective country/language top-level domains. The resulting simple Naive Bayes model, based on less than a thousand word features extracted from web data, outperforms the baseline models in the cross-dataset scenario and achieves good levels of generalization across datasets.
%R 10.18653/v1/2023.vardial-1.11
%U https://aclanthology.org/2023.vardial-1.11
%U https://doi.org/10.18653/v1/2023.vardial-1.11
%P 113-120
Markdown (Informal)
[BENCHić-lang: A Benchmark for Discriminating between Bosnian, Croatian, Montenegrin and Serbian](https://aclanthology.org/2023.vardial-1.11) (Rupnik et al., VarDial 2023)
ACL