@inproceedings{dumitrescu-etal-2020-birth,
title = "The birth of {R}omanian {BERT}",
author = "Dumitrescu, Stefan and
Avram, Andrei-Marius and
Pyysalo, Sampo",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.387",
doi = "10.18653/v1/2020.findings-emnlp.387",
pages = "4324--4328",
abstract = "Large-scale pretrained language models have become ubiquitous in Natural Language Processing. However, most of these models are available either in high-resource languages, in particular English, or as multilingual models that compromise performance on individual languages for coverage. This paper introduces Romanian BERT, the first purely Romanian transformer-based language model, pretrained on a large text corpus. We discuss corpus com-position and cleaning, the model training process, as well as an extensive evaluation of the model on various Romanian datasets. We opensource not only the model itself, but also a repository that contains information on how to obtain the corpus, fine-tune and use this model in production (with practical examples), and how to fully replicate the evaluation process.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dumitrescu-etal-2020-birth">
<titleInfo>
<title>The birth of Romanian BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dumitrescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei-Marius</namePart>
<namePart type="family">Avram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sampo</namePart>
<namePart type="family">Pyysalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale pretrained language models have become ubiquitous in Natural Language Processing. However, most of these models are available either in high-resource languages, in particular English, or as multilingual models that compromise performance on individual languages for coverage. This paper introduces Romanian BERT, the first purely Romanian transformer-based language model, pretrained on a large text corpus. We discuss corpus com-position and cleaning, the model training process, as well as an extensive evaluation of the model on various Romanian datasets. We opensource not only the model itself, but also a repository that contains information on how to obtain the corpus, fine-tune and use this model in production (with practical examples), and how to fully replicate the evaluation process.</abstract>
<identifier type="citekey">dumitrescu-etal-2020-birth</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.387</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.387</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4324</start>
<end>4328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The birth of Romanian BERT
%A Dumitrescu, Stefan
%A Avram, Andrei-Marius
%A Pyysalo, Sampo
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F dumitrescu-etal-2020-birth
%X Large-scale pretrained language models have become ubiquitous in Natural Language Processing. However, most of these models are available either in high-resource languages, in particular English, or as multilingual models that compromise performance on individual languages for coverage. This paper introduces Romanian BERT, the first purely Romanian transformer-based language model, pretrained on a large text corpus. We discuss corpus com-position and cleaning, the model training process, as well as an extensive evaluation of the model on various Romanian datasets. We opensource not only the model itself, but also a repository that contains information on how to obtain the corpus, fine-tune and use this model in production (with practical examples), and how to fully replicate the evaluation process.
%R 10.18653/v1/2020.findings-emnlp.387
%U https://aclanthology.org/2020.findings-emnlp.387
%U https://doi.org/10.18653/v1/2020.findings-emnlp.387
%P 4324-4328
Markdown (Informal)
[The birth of Romanian BERT](https://aclanthology.org/2020.findings-emnlp.387) (Dumitrescu et al., Findings 2020)
ACL
- Stefan Dumitrescu, Andrei-Marius Avram, and Sampo Pyysalo. 2020. The birth of Romanian BERT. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4324–4328, Online. Association for Computational Linguistics.