@inproceedings{masala-etal-2020-robert,
title = "{R}o{BERT} {--} A {R}omanian {BERT} Model",
author = "Masala, Mihai and
Ruseti, Stefan and
Dascalu, Mihai",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.581",
doi = "10.18653/v1/2020.coling-main.581",
pages = "6626--6637",
abstract = "Deep pre-trained language models tend to become ubiquitous in the field of Natural Language Processing (NLP). These models learn contextualized representations by using a huge amount of unlabeled text data and obtain state of the art results on a multitude of NLP tasks, by enabling efficient transfer learning. For other languages besides English, there are limited options of such models, most of which are trained only on multi-lingual corpora. In this paper we introduce a Romanian-only pre-trained BERT model {--} RoBERT {--} and compare it with different multi-lingual models on seven Romanian specific NLP tasks grouped into three categories, namely: sentiment analysis, dialect and cross-dialect topic identification, and diacritics restoration. Our model surpasses the multi-lingual models, as well as a another mono-lingual implementation of BERT, on all tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masala-etal-2020-robert">
<titleInfo>
<title>RoBERT – A Romanian BERT Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Masala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ruseti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Dascalu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep pre-trained language models tend to become ubiquitous in the field of Natural Language Processing (NLP). These models learn contextualized representations by using a huge amount of unlabeled text data and obtain state of the art results on a multitude of NLP tasks, by enabling efficient transfer learning. For other languages besides English, there are limited options of such models, most of which are trained only on multi-lingual corpora. In this paper we introduce a Romanian-only pre-trained BERT model – RoBERT – and compare it with different multi-lingual models on seven Romanian specific NLP tasks grouped into three categories, namely: sentiment analysis, dialect and cross-dialect topic identification, and diacritics restoration. Our model surpasses the multi-lingual models, as well as a another mono-lingual implementation of BERT, on all tasks.</abstract>
<identifier type="citekey">masala-etal-2020-robert</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.581</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.581</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6626</start>
<end>6637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoBERT – A Romanian BERT Model
%A Masala, Mihai
%A Ruseti, Stefan
%A Dascalu, Mihai
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F masala-etal-2020-robert
%X Deep pre-trained language models tend to become ubiquitous in the field of Natural Language Processing (NLP). These models learn contextualized representations by using a huge amount of unlabeled text data and obtain state of the art results on a multitude of NLP tasks, by enabling efficient transfer learning. For other languages besides English, there are limited options of such models, most of which are trained only on multi-lingual corpora. In this paper we introduce a Romanian-only pre-trained BERT model – RoBERT – and compare it with different multi-lingual models on seven Romanian specific NLP tasks grouped into three categories, namely: sentiment analysis, dialect and cross-dialect topic identification, and diacritics restoration. Our model surpasses the multi-lingual models, as well as a another mono-lingual implementation of BERT, on all tasks.
%R 10.18653/v1/2020.coling-main.581
%U https://aclanthology.org/2020.coling-main.581
%U https://doi.org/10.18653/v1/2020.coling-main.581
%P 6626-6637
Markdown (Informal)
[RoBERT – A Romanian BERT Model](https://aclanthology.org/2020.coling-main.581) (Masala et al., COLING 2020)
ACL
- Mihai Masala, Stefan Ruseti, and Mihai Dascalu. 2020. RoBERT – A Romanian BERT Model. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6626–6637, Barcelona, Spain (Online). International Committee on Computational Linguistics.