@inproceedings{servan-etal-2024-malbert-compact,
title = "m{ALBERT}: Is a Compact Multilingual {BERT} Model Still Worth It?",
author = "Servan, Christophe and
Ghannay, Sahar and
Rosset, Sophie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.960",
pages = "11023--11029",
abstract = "Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical and ecological impact of such models. In this article, considering these critical remarks, we propose to focus on smaller models, such as compact models like ALBERT, which are more ecologically virtuous than these PLM. However, PLMs enable huge breakthroughs in Natural Language Processing tasks, such as Spoken and Natural Language Understanding, classification, Question{--}Answering tasks. PLMs also have the advantage of being multilingual, and, as far as we know, a multilingual version of compact ALBERT models does not exist. Considering these facts, we propose the free release of the first version of a multilingual compact ALBERT model, pre-trained using Wikipedia data, which complies with the ethical aspect of such a language model. We also evaluate the model against classical multilingual PLMs in classical NLP tasks. Finally, this paper proposes a rare study on the subword tokenization impact on language performances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="servan-etal-2024-malbert-compact">
<titleInfo>
<title>mALBERT: Is a Compact Multilingual BERT Model Still Worth It?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Servan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical and ecological impact of such models. In this article, considering these critical remarks, we propose to focus on smaller models, such as compact models like ALBERT, which are more ecologically virtuous than these PLM. However, PLMs enable huge breakthroughs in Natural Language Processing tasks, such as Spoken and Natural Language Understanding, classification, Question–Answering tasks. PLMs also have the advantage of being multilingual, and, as far as we know, a multilingual version of compact ALBERT models does not exist. Considering these facts, we propose the free release of the first version of a multilingual compact ALBERT model, pre-trained using Wikipedia data, which complies with the ethical aspect of such a language model. We also evaluate the model against classical multilingual PLMs in classical NLP tasks. Finally, this paper proposes a rare study on the subword tokenization impact on language performances.</abstract>
<identifier type="citekey">servan-etal-2024-malbert-compact</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.960</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11023</start>
<end>11029</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mALBERT: Is a Compact Multilingual BERT Model Still Worth It?
%A Servan, Christophe
%A Ghannay, Sahar
%A Rosset, Sophie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F servan-etal-2024-malbert-compact
%X Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical and ecological impact of such models. In this article, considering these critical remarks, we propose to focus on smaller models, such as compact models like ALBERT, which are more ecologically virtuous than these PLM. However, PLMs enable huge breakthroughs in Natural Language Processing tasks, such as Spoken and Natural Language Understanding, classification, Question–Answering tasks. PLMs also have the advantage of being multilingual, and, as far as we know, a multilingual version of compact ALBERT models does not exist. Considering these facts, we propose the free release of the first version of a multilingual compact ALBERT model, pre-trained using Wikipedia data, which complies with the ethical aspect of such a language model. We also evaluate the model against classical multilingual PLMs in classical NLP tasks. Finally, this paper proposes a rare study on the subword tokenization impact on language performances.
%U https://aclanthology.org/2024.lrec-main.960
%P 11023-11029
Markdown (Informal)
[mALBERT: Is a Compact Multilingual BERT Model Still Worth It?](https://aclanthology.org/2024.lrec-main.960) (Servan et al., LREC-COLING 2024)
ACL
- Christophe Servan, Sahar Ghannay, and Sophie Rosset. 2024. mALBERT: Is a Compact Multilingual BERT Model Still Worth It?. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11023–11029, Torino, Italia. ELRA and ICCL.