@inproceedings{kamal-eddine-etal-2021-barthez,
title = "{BART}hez: a Skilled Pretrained {F}rench Sequence-to-Sequence Model",
author = "Kamal Eddine, Moussa and
Tixier, Antoine and
Vazirgiannis, Michalis",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.740",
doi = "10.18653/v1/2021.emnlp-main.740",
pages = "9369--9390",
abstract = "Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the available models and research have been conducted for English. In this work, we introduce BARThez, the first large-scale pretrained seq2seq model for French. Being based on BART, BARThez is particularly well-suited for generative tasks. We evaluate BARThez on five discriminative tasks from the FLUE benchmark and two generative tasks from a novel summarization dataset, OrangeSum, that we created for this research. We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT. We also continue the pretraining of a multilingual BART on BARThez{'} corpus, and show our resulting model, mBARThez, to significantly boost BARThez{'} generative performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamal-eddine-etal-2021-barthez">
<titleInfo>
<title>BARThez: a Skilled Pretrained French Sequence-to-Sequence Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moussa</namePart>
<namePart type="family">Kamal Eddine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Tixier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michalis</namePart>
<namePart type="family">Vazirgiannis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the available models and research have been conducted for English. In this work, we introduce BARThez, the first large-scale pretrained seq2seq model for French. Being based on BART, BARThez is particularly well-suited for generative tasks. We evaluate BARThez on five discriminative tasks from the FLUE benchmark and two generative tasks from a novel summarization dataset, OrangeSum, that we created for this research. We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT. We also continue the pretraining of a multilingual BART on BARThez’ corpus, and show our resulting model, mBARThez, to significantly boost BARThez’ generative performance.</abstract>
<identifier type="citekey">kamal-eddine-etal-2021-barthez</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.740</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.740</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9369</start>
<end>9390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
%A Kamal Eddine, Moussa
%A Tixier, Antoine
%A Vazirgiannis, Michalis
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F kamal-eddine-etal-2021-barthez
%X Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the available models and research have been conducted for English. In this work, we introduce BARThez, the first large-scale pretrained seq2seq model for French. Being based on BART, BARThez is particularly well-suited for generative tasks. We evaluate BARThez on five discriminative tasks from the FLUE benchmark and two generative tasks from a novel summarization dataset, OrangeSum, that we created for this research. We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT. We also continue the pretraining of a multilingual BART on BARThez’ corpus, and show our resulting model, mBARThez, to significantly boost BARThez’ generative performance.
%R 10.18653/v1/2021.emnlp-main.740
%U https://aclanthology.org/2021.emnlp-main.740
%U https://doi.org/10.18653/v1/2021.emnlp-main.740
%P 9369-9390
Markdown (Informal)
[BARThez: a Skilled Pretrained French Sequence-to-Sequence Model](https://aclanthology.org/2021.emnlp-main.740) (Kamal Eddine et al., EMNLP 2021)
ACL
- Moussa Kamal Eddine, Antoine Tixier, and Michalis Vazirgiannis. 2021. BARThez: a Skilled Pretrained French Sequence-to-Sequence Model. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9369–9390, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.