@inproceedings{sido-etal-2021-czert,
title = "Czert {--} {C}zech {BERT}-like Model for Language Representation",
author = "Sido, Jakub and
Pra{\v{z}}{\'a}k, Ond{\v{r}}ej and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Pa{\v{s}}ek, Jan and
Sej{\'a}k, Michal and
Konop{\'\i}k, Miloslav",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.149",
pages = "1326--1338",
abstract = "This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures. We pre-train our models on more than 340K of sentences, which is 50 times more than multilingual models that include Czech data. We outperform the multilingual models on 9 out of 11 datasets. In addition, we establish the new state-of-the-art results on nine datasets. At the end, we discuss properties of monolingual and multilingual models based upon our results. We publish all the pre-trained and fine-tuned models freely for the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sido-etal-2021-czert">
<titleInfo>
<title>Czert – Czech BERT-like Model for Language Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Sido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Pražák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Pašek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Seják</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloslav</namePart>
<namePart type="family">Konopík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures. We pre-train our models on more than 340K of sentences, which is 50 times more than multilingual models that include Czech data. We outperform the multilingual models on 9 out of 11 datasets. In addition, we establish the new state-of-the-art results on nine datasets. At the end, we discuss properties of monolingual and multilingual models based upon our results. We publish all the pre-trained and fine-tuned models freely for the research community.</abstract>
<identifier type="citekey">sido-etal-2021-czert</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.149</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>1326</start>
<end>1338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Czert – Czech BERT-like Model for Language Representation
%A Sido, Jakub
%A Pražák, Ondřej
%A Přibáň, Pavel
%A Pašek, Jan
%A Seják, Michal
%A Konopík, Miloslav
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F sido-etal-2021-czert
%X This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures. We pre-train our models on more than 340K of sentences, which is 50 times more than multilingual models that include Czech data. We outperform the multilingual models on 9 out of 11 datasets. In addition, we establish the new state-of-the-art results on nine datasets. At the end, we discuss properties of monolingual and multilingual models based upon our results. We publish all the pre-trained and fine-tuned models freely for the research community.
%U https://aclanthology.org/2021.ranlp-1.149
%P 1326-1338
Markdown (Informal)
[Czert – Czech BERT-like Model for Language Representation](https://aclanthology.org/2021.ranlp-1.149) (Sido et al., RANLP 2021)
ACL
- Jakub Sido, Ondřej Pražák, Pavel Přibáň, Jan Pašek, Michal Seják, and Miloslav Konopík. 2021. Czert – Czech BERT-like Model for Language Representation. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1326–1338, Held Online. INCOMA Ltd..