@inproceedings{ljubesic-lauc-2021-bertic,
title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Lauc, Davor",
editor = "Babych, Bogdan and
Kanishcheva, Olga and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
Starko, Vasyl and
Steinberger, Josef and
Yangarber, Roman and
Marci{\'n}czuk, Micha{\l} and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Robnik-{\v{S}}ikonja, Marko",
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bsnlp-1.5",
pages = "37--42",
abstract = "In this paper we describe a transformer model pre-trained on 8 billion tokens of crawled text from the Croatian, Bosnian, Serbian and Montenegrin web domains. We evaluate the transformer model on the tasks of part-of-speech tagging, named-entity-recognition, geo-location prediction and commonsense causal reasoning, showing improvements on all tasks over state-of-the-art models. For commonsense reasoning evaluation we introduce COPA-HR - a translation of the Choice of Plausible Alternatives (COPA) dataset into Croatian. The BERTi{\'c} model is made available for free usage and further task-specific fine-tuning through HuggingFace.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-lauc-2021-bertic">
<titleInfo>
<title>BERTić - The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davor</namePart>
<namePart type="family">Lauc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kanishcheva</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">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasyl</namePart>
<namePart type="family">Starko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Robnik-Šikonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe a transformer model pre-trained on 8 billion tokens of crawled text from the Croatian, Bosnian, Serbian and Montenegrin web domains. We evaluate the transformer model on the tasks of part-of-speech tagging, named-entity-recognition, geo-location prediction and commonsense causal reasoning, showing improvements on all tasks over state-of-the-art models. For commonsense reasoning evaluation we introduce COPA-HR - a translation of the Choice of Plausible Alternatives (COPA) dataset into Croatian. The BERTić model is made available for free usage and further task-specific fine-tuning through HuggingFace.</abstract>
<identifier type="citekey">ljubesic-lauc-2021-bertic</identifier>
<location>
<url>https://aclanthology.org/2021.bsnlp-1.5</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>37</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERTić - The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian
%A Ljubešić, Nikola
%A Lauc, Davor
%Y Babych, Bogdan
%Y Kanishcheva, Olga
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Starko, Vasyl
%Y Steinberger, Josef
%Y Yangarber, Roman
%Y Marcińczuk, Michał
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Robnik-Šikonja, Marko
%S Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F ljubesic-lauc-2021-bertic
%X In this paper we describe a transformer model pre-trained on 8 billion tokens of crawled text from the Croatian, Bosnian, Serbian and Montenegrin web domains. We evaluate the transformer model on the tasks of part-of-speech tagging, named-entity-recognition, geo-location prediction and commonsense causal reasoning, showing improvements on all tasks over state-of-the-art models. For commonsense reasoning evaluation we introduce COPA-HR - a translation of the Choice of Plausible Alternatives (COPA) dataset into Croatian. The BERTić model is made available for free usage and further task-specific fine-tuning through HuggingFace.
%U https://aclanthology.org/2021.bsnlp-1.5
%P 37-42
Markdown (Informal)
[BERTić - The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian](https://aclanthology.org/2021.bsnlp-1.5) (Ljubešić & Lauc, BSNLP 2021)
ACL